© 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. 58003
    Prev
    Next
    INDEX
    Explanations

    affiliation descriptions

    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
     action
    -0.76
     begin
    -0.73
    っちゃった
    -0.72
    ὃ
    -0.71
    はは
    -0.71
     vogue
    -0.70
     allow
    -0.70
    Sv
    -0.70
    Aerial
    -0.70
     قابل
    -0.69
    POSITIVE LOGITS
    下载附件
    0.94
    UNRELATED
    0.93
    \},
    0.90
    ,:,
    0.85
     BORROW
    0.84
    ﾘ
    0.82
    嘉宾
    0.81
    */,
    0.81
    Hmm
    0.80
    までの
    0.80
    Activations Density 0.002%

    No Known Activations