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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 363
    Prev
    Next
    INDEX
    Explanations

    rational roots, shuffle, symbolism, personalization, cheaply

    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
    낍
    1.39
     dikeluarkan
    1.33
    퍁
    1.32
    𒐁
    1.30
    另
    1.29
    ►
    1.28
    cccn
    1.28
    𒃼
    1.26
    𒋩
    1.25
    %),
    1.25
    POSITIVE LOGITS
     of
    0.85
     å
    0.79
     as
    0.77
    ্ব
    0.74
     ple
    0.74
    Brand
    0.73
    inging
    0.73
     Brand
    0.73
     infinite
    0.73
    ্বে
    0.72
    Activations Density 0.000%

    No Known Activations