© 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. 93333
    Prev
    Next
    INDEX
    Explanations

    building blocks

    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
    mità
    -0.72
    abilir
    -0.67
     GS
    -0.65
    joyed
    -0.64
    hütte
    -0.63
    inese
    -0.63
    pless
    -0.62
    ӕ
    -0.61
    bottomrule
    -0.61
    NSFW
    -0.61
    POSITIVE LOGITS
     blocks
    4.94
     block
    4.56
    blocks
    4.25
     Blocks
    3.92
    block
    3.92
    Blocks
    3.86
    Block
    3.48
     Block
    3.39
    ブロック
    3.34
     BLOCK
    3.28
    Activations Density 0.053%

    No Known Activations