© 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. 549
    Prev
    Next
    INDEX
    Explanations

    genetic algorithm, orange

    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
    Im
    3.04
     速
    3.01
     Strategy
    2.81
     strategy
    2.77
     strategies
    2.76
    &-
    2.75
    Organisation
    2.74
     Strategies
    2.73
     Vee
    2.73
    Mit
    2.72
    POSITIVE LOGITS
     inanimate
    2.87
    当該
    2.51
     unoccupied
    2.48
    quetas
    2.40
     unprocessed
    2.34
    asilkan
    2.33
    rinsic
    2.27
    ฺ
    2.25
    ammelt
    2.23
    תוך
    2.22
    Activations Density 1.194%

    No Known Activations