© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20082
    Prev
    Next
    INDEX
    Explanations

    extensive use

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specializes in spotting English adjectives ending in the “-ous” suffix.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    uncommon or foreign-language tokens, especially elevated adjectives/adverbs with formal suffixes.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    words indicating abundance or large quantities, particularly "copious" and "correspondingly".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    硯
    -2.58
    t
    -2.55
    ᎒
    -2.50
    dzić
    -2.33
    derdag
    -2.31
     Somehow
    -2.28
     This
    -2.28
    媖
    -2.22
     There
    -2.22
     ésta
    -2.20
    POSITIVE LOGITS
     ")";
    2.48
    鱨
    2.48
    甞
    2.28
     него
    2.16
     "}";
    2.11
    0
    2.06
    </strong>
    2.06
     {
    2.05
    
    2.03
     “
    2.02
    Activations Density 0.001%

    No Known Activations