© 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. 63966
    Prev
    Next
    INDEX
    Explanations

    exceptional performance or timely actions

    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
    inSlope
    -0.81
    orative
    -0.81
     Kompon
    -0.81
    rapp
    -0.80
    ров
    -0.79
    rily
    -0.78
    𝙐
    -0.78
    Ů
    -0.77
    mands
    -0.74
    ณฑ
    -0.74
    POSITIVE LOGITS
     saves
    1.98
     save
    1.98
    save
    1.76
    Save
    1.49
     Save
    1.48
     finish
    1.33
     Saves
    1.30
    saves
    1.30
     SAVE
    1.29
     stop
    1.27
    Activations Density 0.033%

    No Known Activations