© 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. 246102
    Prev
    Next
    INDEX
    Explanations

    choices between options

    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
     বন্দরে
    0.52
    alakip
    0.48
     آهي
    0.47
    ANDA
    0.46
    PREFIX
    0.45
    axs
    0.45
     মনোযোগ
    0.45
     為
    0.43
    omely
    0.43
     مصروف
    0.43
    POSITIVE LOGITS
     ullam
    0.47
     Dism
    0.47
    व
    0.47
     opportunità
    0.45
    кли
    0.45
    Horizon
    0.45
    Umb
    0.44
    గాలు
    0.43
    Found
    0.43
    Jam
    0.43
    Activations Density 0.000%

    No Known Activations