© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 164139
    Prev
    Next
    INDEX
    Explanations

    purpose of, every kind of

    np_acts-logits-general · gemini-2.5-flash-lite

    database, movies, and predictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dió
    0.50
     belts
    0.49
    ВД
    0.47
    mère
    0.47
    也不是
    0.46
     corset
    0.46
    帘
    0.46
    өл
    0.45
    dü
    0.45
    妊
    0.45
    POSITIVE LOGITS
    </h2>
    0.54
     pagare
    0.49
     SUM
    0.47
     dibujar
    0.46
    invest
    0.46
    </h1>
    0.46
    </h3>
    0.45
     ચૂક
    0.44
    find
    0.43
     successo
    0.43
    Activations Density 0.001%

    No Known Activations