© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46781
    Prev
    Next
    INDEX
    Explanations

    lists, conjunctions, and diverse scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mensuales
    0.48
     baterías
    0.45
     исследова
    0.43
    見た
    0.42
     democracia
    0.42
     demuestra
    0.41
    getMonth
    0.41
    貧
    0.41
     corrupción
    0.40
     negros
    0.40
    POSITIVE LOGITS
     通过
    0.42
     ओर
    0.41
     Architectural
    0.39
     为了
    0.39
    อป
    0.38
    Ē
    0.37
    लैंड
    0.37
    简化
    0.37
     Lets
    0.37
    ǿ
    0.37
    Activations Density 0.016%

    No Known Activations