© 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. 59799
    Prev
    Next
    INDEX
    Explanations

    long long integer suffix

    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
    providedIn
    -2.39
    ቾ
    -2.16
     *}
    -1.91
    قية
    -1.88
     }_{\
    -1.85
    翆
    -1.82
    輒
    -1.82
    centerTitle
    -1.80
    辄
    -1.80
    笮
    -1.80
    POSITIVE LOGITS
     
    1.94
     Antrags
    1.94
    ",
    1.93
    要
    1.85
     Ngày
    1.84
    You
    1.84
    selbe
    1.81
     Änder
    1.80
    If
    1.77
     \%
    1.77
    Activations Density 0.002%

    No Known Activations