© 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. 10-GEMMASCOPE-RES-131K
    7. 42862
    Prev
    Next
    INDEX
    Explanations

    heavy metal band

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

    The neuron fires on the main content noun (the head noun) of multi‐word technical or topical phrases.

    oai_token-act-pair · o4-miniTriggered 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
     fön
    -1.45
     its
    -1.42
     confund
    -1.41
     your
    -1.40
    ,”
    -1.38
    ",
    -1.27
    ”.
    -1.26
    </
    -1.25
     sprend
    -1.24
     holdt
    -1.23
    POSITIVE LOGITS
    Many
    1.43
    可爱的
    1.26
     skirting
    1.26
     儿童
    1.25
     對
    1.24
    许多
    1.24
     massacres
    1.23
     bedeckt
    1.22
     creando
    1.21
     seluruh
    1.20
    Activations Density 0.754%

    No Known Activations