© 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. 107107
    Prev
    Next
    INDEX
    Explanations

    numbers and slashes

    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
     pin
    -0.85
    ᶦ
    -0.83
     how
    -0.81
    nteral
    -0.81
    inom
    -0.80
    頃
    -0.80
     buck
    -0.80
     broad
    -0.79
     celor
    -0.78
     głoś
    -0.77
    POSITIVE LOGITS
    っぱり
    0.80
    ߲
    0.79
     Wants
    0.75
     chitar
    0.74
     DEFINITIONS
    0.73
     PHOSPH
    0.73
     Crucifix
    0.73
    chtige
    0.73
     SCALE
    0.73
     عض
    0.72
    Activations Density 0.097%

    No Known Activations