© 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. 102295
    Prev
    Next
    INDEX
    Explanations

    different than

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

    explaining factual sequences

    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
    offer
    0.49
     ज
    0.48
     बसी
    0.48
    면에
    0.48
    鮋
    0.47
    ayı
    0.46
    atik
    0.46
    ounds
    0.46
    abas
    0.45
     सप
    0.45
    POSITIVE LOGITS
     rescaling
    0.47
    ALERT
    0.46
    事は
    0.45
     developmental
    0.45
    両
    0.44
    出来る
    0.44
     surveillance
    0.44
     rayonnement
    0.44
    ’
    0.44
     turnover
    0.43
    Activations Density 0.001%

    No Known Activations