© 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. 19196
    Prev
    Next
    INDEX
    Explanations

    a after small words

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

    RSVP by, LTL Shipping, Pros of

    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
     postulated
    0.54
    ድር
    0.50
    蹂
    0.50
    Кор
    0.48
     resulting
    0.46
    लोर
    0.44
    Outcome
    0.44
    พิมพ์
    0.44
     Стар
    0.43
    ประ
    0.43
    POSITIVE LOGITS
     olho
    0.52
     iluminación
    0.46
    x
    0.45
    q
    0.45
    zcan
    0.44
     Türk
    0.44
    %%%%
    0.43
    মেল
    0.43
     Spurs
    0.43
     Gegensatz
    0.42
    Activations Density 0.000%

    No Known Activations