© 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. 4724
    Prev
    Next
    INDEX
    Explanations

    evaluating properties and effectiveness

    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
     Bagaimana
    0.63
    ка
    0.54
    do
    0.54
    hi
    0.53
     Jangan
    0.51
     Какие
    0.51
    포
    0.51
    omio
    0.51
    Ⅰ
    0.51
    can
    0.50
    POSITIVE LOGITS
     scalars
    0.60
     explos
    0.55
     phonons
    0.55
     polymers
    0.54
     axles
    0.54
     colonialism
    0.52
     metaphors
    0.52
     pollinators
    0.52
     ontological
    0.52
     axonal
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.