© 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. 71834
    Prev
    Next
    INDEX
    Explanations

    prehistoric counterpartsfor smallwhich isamong thetemporary refugefor roofingeven ifyou mustcorresponding numbered

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

    Japan's militarism and expansionism

    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
     lavar
    0.48
    artan
    0.46
     ដោយ
    0.45
    រួ
    0.45
    🅽
    0.44
    诟
    0.44
    পাতালে
    0.43
    щины
    0.43
    肿
    0.42
     separación
    0.42
    POSITIVE LOGITS
     همد
    0.48
    リアル
    0.40
    系の
    0.40
    unexpected
    0.40
    نامه
    0.40
    貽
    0.39
    みたいな
    0.39
     assemblage
    0.39
    bible
    0.39
     انب
    0.38
    Activations Density 0.000%

    No Known Activations