© 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. 107116
    Prev
    Next
    INDEX
    Explanations

    code blocks and programming comments

    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
     graham
    -0.81
    Requester
    -0.68
    misión
    -0.66
    ㅌ
    -0.65
     ケーキ
    -0.65
    ResponseCode
    -0.65
    ͜
    -0.63
    МІ
    -0.63
    ウンジ
    -0.63
     excision
    -0.63
    POSITIVE LOGITS
    endront
    0.76
     wor
    0.73
    skem
    0.73
    pexpr
    0.72
    aksana
    0.72
    Ἠ
    0.69
    morphic
    0.65
     Ordner
    0.64
    hew
    0.64
    newpage
    0.63
    Activations Density 0.225%

    No Known Activations