© 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. 100696
    Prev
    Next
    INDEX
    Explanations

    specific categories and outcomes

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

    list formatting and direct explanation

    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
    arens
    0.47
    㚼
    0.47
    ೇಯ
    0.46
    ugging
    0.45
    cando
    0.44
    cations
    0.44
    రోగ
    0.44
    िकारक
    0.44
    叱
    0.44
    ediat
    0.43
    POSITIVE LOGITS
     integer
    0.54
     troubled
    0.54
    فی
    0.50
     MONT
    0.50
     mont
    0.49
     homeless
    0.49
     unmanned
    0.49
     appended
    0.48
     sauf
    0.47
    MONT
    0.47
    Activations Density 0.001%

    No Known Activations