© 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. 117657
    Prev
    Next
    INDEX
    Explanations

    out

    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
    nė
    -0.88
    pă
    -0.84
     ușor
    -0.84
     instead
    -0.83
    $​
    -0.80
    plateau
    -0.79
     surety
    -0.79
     daž
    -0.79
     papild
    -0.77
    ホル
    -0.77
    POSITIVE LOGITS
     Out
    0.88
    out
    0.84
    average
    0.83
    斯基
    0.79
    Out
    0.79
    ি
    0.76
    意料
    0.76
    tées
    0.74
    잼
    0.74
     че
    0.73
    Activations Density 0.053%

    No Known Activations