© 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. 191490
    Prev
    Next
    INDEX
    Explanations

    steps, entry descriptions, found

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

    revelations building, he perceives, sending, exists the, apartments

    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
     Carvalho
    0.55
     ἢ
    0.51
     Het
    0.50
     À
    0.47
    tro
    0.46
    im
    0.45
     Imam
    0.44
    te
    0.43
     caravan
    0.43
     T
    0.43
    POSITIVE LOGITS
    year
    0.45
    YEAR
    0.45
    ఋ
    0.43
    MONTH
    0.43
    два
    0.42
     TESTS
    0.42
    িশ
    0.42
    సారి
    0.42
    マーケット
    0.41
    LAY
    0.41
    Activations Density 0.003%

    No Known Activations