© 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. 134462
    Prev
    Next
    INDEX
    Explanations

    still goes

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

    aligns with, require massive

    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
    hausen
    0.45
    isak
    0.44
     యూ
    0.44
    boton
    0.44
    jag
    0.43
    %");
    0.43
    acharya
    0.43
    EM
    0.42
     Hochsch
    0.41
     Republik
    0.41
    POSITIVE LOGITS
    ቮ
    0.48
    際の
    0.47
    歳の
    0.47
    ດ້ານ
    0.47
    Section
    0.46
     ağı
    0.46
     związane
    0.46
     opération
    0.45
    찮
    0.45
    ດ້
    0.44
    Activations Density 0.001%

    No Known Activations