© 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. 47962
    Prev
    Next
    INDEX
    Explanations

    level, class, that, 9, Into, maio, 1, player

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

    prejudice and negations

    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
    防护
    0.47
    -
    0.46
    eli
    0.45
    ackle
    0.42
    ittings
    0.41
    អនុ
    0.40
     aten
    0.39
     الجنس
    0.39
     कार्यक्रमा
    0.39
     protezione
    0.38
    POSITIVE LOGITS
     contends
    0.46
     negated
    0.46
    ریک
    0.45
    صير
    0.43
    m
    0.43
     idxf
    0.42
     poziom
    0.41
    হ
    0.41
    Monty
    0.41
    աշ
    0.41
    Activations Density 0.000%

    No Known Activations