© 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. 186259
    Prev
    Next
    INDEX
    Explanations

    completions

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

    knots, system measurement

    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
     Jacobsen
    0.46
     organisation
    0.45
    glichen
    0.45
     timescale
    0.44
    에는
    0.43
    猷
    0.43
     घरात
    0.42
    പ്പ
    0.41
     زمانے
    0.41
     trp
    0.41
    POSITIVE LOGITS
    ouvoir
    0.50
    体重
    0.46
     tragically
    0.46
    accarat
    0.46
    addPreferred
    0.45
    ars
    0.44
     conhece
    0.44
    >";
    0.43
     conhecido
    0.42
    lickr
    0.42
    Activations Density 0.001%

    No Known Activations