© 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. 99705
    Prev
    Next
    INDEX
    Explanations

    names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ?
    -3.45
    ).
    -3.41
    e
    -3.38
    ",
    -2.86
    ):
    -2.81
    1
    -2.73
     مثل
    -2.70
    –
    -2.61
     этот
    -2.56
    _
    -2.45
    POSITIVE LOGITS
    leggio
    3.16
     čím
    2.94
    鮃
    2.63
    いれば
    2.61
    と言える
    2.58
    其妙
    2.55
     proč
    2.53
    viembre
    2.53
     Therefore
    2.53
     gustaMe
    2.52
    Activations Density 0.022%

    No Known Activations