© 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. 187590
    Prev
    Next
    INDEX
    Explanations

    refunds, replacements, and exchanges

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

    can discuss or estimate

    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
    G
    0.67
    C
    0.65
    In
    0.61
    A
    0.61
    The
    0.60
    B
    0.59
    the
    0.57
    M
    0.57
    Williams
    0.56
    R
    0.56
    POSITIVE LOGITS
     chargingStation
    0.69
     mutex
    0.64
     speechSynthesis
    0.64
     literals
    0.62
     confuses
    0.56
     commandBuffer
    0.55
     conflit
    0.55
     dragState
    0.54
    Ყ
    0.54
     conflictos
    0.54
    Activations Density 0.000%

    No Known Activations