© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56821
    Prev
    Next
    INDEX
    Explanations

    pushing boundaries and turning tides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     The
    0.68
    the
    0.61
     the
    0.60
    The
    0.56
    ’
    0.50
    ses
    0.49
    sembl
    0.49
     facsimile
    0.49
    i
    0.49
     me
    0.48
    POSITIVE LOGITS
     of
    0.58
    ContainsKey
    0.53
     của
    0.52
    ೋತಿ
    0.51
     của
    0.50
    ของการ
    0.49
    ாய்
    0.49
    ан
    0.49
    AppBar
    0.49
    ியார்
    0.48
    Activations Density 0.062%

    No Known Activations