© 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. 247990
    Prev
    Next
    INDEX
    Explanations

    prediction, clarification, negation

    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
     डी
    0.54
     वास्तविकता
    0.50
    ມັນ
    0.48
    阌
    0.48
     ответы
    0.47
     मुश्किल
    0.46
    ūt
    0.46
     कंटिन्यू
    0.46
     đoán
    0.45
    ۔
    0.44
    POSITIVE LOGITS
    奢
    0.46
     brib
    0.45
    צל
    0.44
     napp
    0.44
    ➙
    0.43
     subl
    0.43
    >
    0.43
     Anglican
    0.41
     assass
    0.41
    סי
    0.41
    Activations Density 0.000%

    No Known Activations