© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1985
    Prev
    Next
    INDEX
    Explanations

    existing heart, core logic, current depth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_65k_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
    0.87
    <0xF3>
    0.83
     a
    0.83
    A
    0.79
    For
    0.77
     Untuk
    0.76
    Untuk
    0.76
     for
    0.75
    E
    0.74
    An
    0.74
    POSITIVE LOGITS
    <unused374>
    0.98
     struggles
    0.93
    MSFont
    0.92
    """"""""
    0.90
    ╅
    0.90
    হৃত
    0.89
    <unused1759>
    0.89
    وون
    0.89
    <unused1844>
    0.89
     strengths
    0.88
    Activations Density 0.936%

    No Known Activations