© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 541
    Prev
    Next
    INDEX
    Explanations

    less is more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     J
    0.79
     L
    0.77
     a
    0.77
     Da
    0.72
     A
    0.71
     Val
    0.70
     Ma
    0.66
     Na
    0.64
    했다
    0.63
     an
    0.63
    POSITIVE LOGITS
    <unused1219>
    1.01
    ꩡ
    0.98
     فونب
    0.97
    <unused1631>
    0.97
    <unused764>
    0.96
    ATIC
    0.96
    skcipher
    0.95
    ynomial
    0.95
    ccncc
    0.95
    <unused1909>
    0.93
    Activations Density 1.193%

    No Known Activations