© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1980
    Prev
    Next
    INDEX
    Explanations

    code printing and function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     ब
    0.58
     timeout
    0.57
     {'
    0.55
     newline
    0.55
    abc
    0.54
    Strawberry
    0.53
     Cucumber
    0.53
     Timeout
    0.53
    ApiKey
    0.52
    abcdef
    0.51
    POSITIVE LOGITS
    <unused2117>
    0.68
     تعط
    0.64
    chodu
    0.61
    <unused2178>
    0.60
    <unused2121>
    0.60
     odnos
    0.59
    <unused217>
    0.58
    <unused1009>
    0.58
    чера
    0.57
    <unused573>
    0.56
    Activations Density 0.071%

    No Known Activations