© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 557
    Prev
    Next
    INDEX
    Explanations

    programmer code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Triv
    1.95
     Tipp
    1.83
     („
    1.73
    !<
    1.73
     Enlarg
    1.71
     amma
    1.70
     Ens
    1.70
    囝
    1.69
    Looks
    1.69
    Im
    1.67
    POSITIVE LOGITS
    _
    2.43
    _{
    1.07
    _+
    0.99
    \_
    0.98
    8
    0.98
    3
    0.97
    quetas
    0.97
    _*
    0.94
    _\
    0.91
    _-
    0.91
    Activations Density 0.760%

    No Known Activations