© 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. 3114
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    </h1>
    -0.91
    ciosa
    -0.89
    deburg
    -0.88
    "}"
    -0.88
     weird
    -0.87
    kva
    -0.84
     even
    -0.82
    ślę
    -0.81
    delt
    -0.81
    zino
    -0.79
    POSITIVE LOGITS
     accentuated
    1.02
     ốp
    1.00
    undidad
    0.96
     masaj
    0.96
     孫
    0.94
     recklessly
    0.93
    良かったです
    0.92
     vấn
    0.91
     then
    0.90
    ards
    0.89
    Activations Density 0.001%

    No Known Activations