© 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. 236581
    Prev
    Next
    INDEX
    Explanations

    negative states followed by continuations

    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
    ಸ
    0.52
    irli
    0.45
    irán
    0.45
     Phas
    0.45
    ડ
    0.45
     проб
    0.45
    ad
    0.44
    İ
    0.43
    ოვანი
    0.43
    ir
    0.43
    POSITIVE LOGITS
    ঞ্চলে
    0.49
     berkualitas
    0.45
    typically
    0.44
    credibly
    0.43
     बोलते
    0.43
    ঞ্চলের
    0.42
     televis
    0.40
    lickr
    0.40
    徹
    0.40
    igueur
    0.39
    Activations Density 0.001%

    No Known Activations