© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46397
    Prev
    Next
    INDEX
    Explanations

    categorized based on

    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
    s
    0.55
    to
    0.52
    sat
    0.48
    d
    0.45
    by
    0.45
    direction
    0.45
    tests
    0.45
    ut
    0.44
    ”、
    0.44
    ಮ
    0.44
    POSITIVE LOGITS
     suppressor
    0.51
     pequeños
    0.50
     mauris
    0.50
     peque
    0.47
     absolv
    0.46
     dificuldades
    0.46
    isateur
    0.45
    Beverungen
    0.45
     extranjeros
    0.44
    ಲೆಂ
    0.44
    Activations Density 0.000%

    No Known Activations