© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39565
    Prev
    Next
    INDEX
    Explanations

    font names with hyphens

    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
    最後
    -1.09
     IBRARY
    -1.04
     Gründe
    -1.02
    СТВ
    -1.02
    ,
    -1.00
    Hermoso
    -1.00
    俭
    -0.99
    銲
    -0.98
     hopefully
    -0.97
    衕
    -0.97
    POSITIVE LOGITS
    örung
    1.24
     gå
    1.22
    )++;
    1.20
     шесть
    1.15
    Sonstiges
    1.15
    啊啊
    1.15
    /*!
    1.14
     illustrationer
    1.14
    lerinden
    1.14
     if
    1.13
    Activations Density 0.063%

    No Known Activations