© 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. 175693
    Prev
    Next
    INDEX
    Explanations

    fixed at

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

    trauma or art generation

    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
     перечис
    0.50
     الارد
    0.48
     отвеча
    0.47
     disinvestment
    0.46
     expl
    0.46
     অভিনেত্র
    0.45
    鳩
    0.44
     مشینیں
    0.44
    換
    0.44
     insan
    0.44
    POSITIVE LOGITS
     집에
    0.48
    োজ
    0.45
    composable
    0.45
    affiche
    0.45
     traduit
    0.45
    Î
    0.45
     réduit
    0.44
    US
    0.44
    étranger
    0.43
    py
    0.43
    Activations Density 0.000%

    No Known Activations