© 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. 43826
    Prev
    Next
    INDEX
    Explanations

    tap and hold

    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
    երի
    0.45
    ać
    0.44
    an
    0.43
     endoplasmic
    0.43
    a
    0.41
     lagging
    0.40
    ھر
    0.40
    GraphicsUnit
    0.40
    abilität
    0.40
     futile
    0.39
    POSITIVE LOGITS
    🚗
    0.45
    💵
    0.45
    EXIST
    0.44
    Само
    0.44
     разнообраз
    0.44
     eBooks
    0.43
    💰
    0.42
    💳
    0.41
     წ
    0.41
    受験
    0.41
    Activations Density 0.001%

    No Known Activations