© 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. 34-GEMMASCOPE-RES-131K
    7. 117759
    Prev
    Next
    INDEX
    Explanations

    various punctuation and code

    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_34/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
     السياس
    -1.18
     メイク
    -1.08
    周囲
    -1.02
    轩
    -1.00
     demikian
    -0.99
     ciasc
    -0.98
    墮
    -0.96
     Thereafter
    -0.96
     commensurate
    -0.94
    իւ
    -0.94
    POSITIVE LOGITS
     灰色
    1.13
    『
    1.13
    ┆
    1.12
    。）
    1.08
    HEIGHT
    1.06
    hline
    1.05
    𝗮
    1.01
    ämme
    0.96
     ито
    0.96
    Kenapa
    0.94
    Activations Density 0.006%

    No Known Activations