© 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. 22-GEMMASCOPE-2-RES-16K
    7. 4040
    Prev
    Next
    INDEX
    Explanations

    print, verify, check

    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_22_width_16k_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
     convient
    0.76
     көп
    0.76
    邯
    0.74
    conj
    0.70
    зиден
    0.69
     международ
    0.68
     tanta
    0.68
     entour
    0.67
    ကောင်း
    0.65
    startTimestamp
    0.65
    POSITIVE LOGITS
    print
    0.73
     `.
    0.70
     print
    0.67
     Print
    0.66
    Verification
    0.64
     plt
    0.64
     Prediction
    0.64
    iss
    0.63
    Example
    0.63
    Prediction
    0.61
    Activations Density 0.145%

    No Known Activations