© 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. 1451
    Prev
    Next
    INDEX
    Explanations

    topics of finance and matters

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

    defining or explaining

    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
    they
    0.41
    enough
    0.36
     alcuna
    0.36
    through
    0.35
    also
    0.35
    sometimes
    0.35
    数百
    0.35
    []
    0.34
    resulting
    0.34
     ratus
    0.34
    POSITIVE LOGITS
     finances
    0.77
    如何
    0.74
     how
    0.73
     whether
    0.73
     matters
    0.72
     why
    0.70
     economics
    0.68
     behalf
    0.68
    是否
    0.66
     issues
    0.65
    Activations Density 0.724%

    No Known Activations