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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35558
    Prev
    Next
    INDEX
    Explanations

    relatedness or comparison

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

    The neuron flags content-bearing (non‐stop) words—i.e. semantically significant nouns, verbs, and adjectives—while ignoring common function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     薬局
    -1.56
    coloriage
    -1.34
     incredibly
    -1.25
     récemment
    -1.23
     抠
    -1.22
     amazingly
    -1.20
    傒
    -1.20
     素描
    -1.19
     ܪ
    -1.19
     juſ
    -1.19
    POSITIVE LOGITS
     or
    1.94
     are
    1.51
     should
    1.43
     might
    1.38
     at
    1.35
     may
    1.32
     take
    1.28
     in
    1.23
     on
    1.18
     could
    1.17
    Activations Density 0.099%

    No Known Activations