© 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. 17769
    Prev
    Next
    INDEX
    Explanations

    matrimony, Trendelenburg, Horse Cave, polar bears

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

    computer network, travel, counting, acceptable use

    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
    ak
    1.01
    et
    0.91
    ين
    0.91
    та
    0.87
    ש
    0.84
    א
    0.84
    on
    0.79
    is
    0.78
    িন
    0.77
    ın
    0.77
    POSITIVE LOGITS
    “
    0.65
    ，
    0.63
     be
    0.61
     entirety
    0.60
    ?
    0.58
    「
    0.57
    ”
    0.56
     pequeños
    0.56
     parable
    0.55
    本
    0.55
    Activations Density 0.758%

    No Known Activations