© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1941
    Prev
    Next
    INDEX
    Explanations

    yard out, out of, nights out

    np_acts-logits-general · gemini-2.5-flash-lite

    bash shell commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    ्रोत
    0.46
    ১২শ
    0.45
    পোর
    0.45
    முகச்
    0.43
    𝙪
    0.41
     incisions
    0.41
    Benzyloxy
    0.40
    溲
    0.40
    варти
    0.40
    肆章
    0.40
    POSITIVE LOGITS
    trace
    0.63
     Trace
    0.59
     trace
    0.58
    Trace
    0.55
     traces
    0.52
    in
    0.50
    traces
    0.49
     In
    0.48
    In
    0.48
     traced
    0.46
    Activations Density 0.000%

    No Known Activations