© 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. 222105
    Prev
    Next
    INDEX
    Explanations

    compliance with local law

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

    cataloging and assessment

    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
    そもそも
    0.54
    რო
    0.52
    yrıca
    0.51
     ಭ
    0.51
     Arya
    0.49
    rà
    0.49
     Même
    0.47
     أ
    0.47
     Akademii
    0.47
    ignés
    0.46
    POSITIVE LOGITS
     isotropic
    0.47
    だけに
    0.45
     সৌ
    0.43
    ION
    0.41
    ंगामा
    0.40
    BOT
    0.40
    DEPENDENCIA
    0.40
     плодо
    0.40
     которого
    0.39
    ANIA
    0.39
    Activations Density 0.001%

    No Known Activations