© 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. 30404
    Prev
    Next
    INDEX
    Explanations

    mental function, transaction, advice

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

    personal projects

    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
    consol
    0.48
    ettes
    0.46
    ighted
    0.46
    sexual
    0.45
     жесто
    0.44
    ett
    0.43
    ódigo
    0.43
    ✠
    0.42
    忙
    0.41
    ark
    0.41
    POSITIVE LOGITS
    ق
    0.45
     RAI
    0.45
     Saúde
    0.44
    眎
    0.44
     Å
    0.43
    د
    0.43
    م
    0.43
    Ć
    0.43
     藤
    0.43
     Rai
    0.42
    Activations Density 0.000%

    No Known Activations