© 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. 81188
    Prev
    Next
    INDEX
    Explanations

    completed tasks

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

    simple vs complex

    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
     tutaj
    0.47
     abilit
    0.45
    Einzel
    0.44
    เรา
    0.44
    лығы
    0.43
    鲮
    0.43
     astr
    0.43
    িক্ষ
    0.41
    锜
    0.41
     asta
    0.41
    POSITIVE LOGITS
    be
    0.51
    techn
    0.48
    त
    0.47
     хотите
    0.46
    ropol
    0.46
    effectively
    0.46
    increase
    0.46
     धु
    0.45
    perman
    0.44
    occupation
    0.44
    Activations Density 0.003%

    No Known Activations