© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1916
    Prev
    Next
    INDEX
    Explanations

    introduces clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
     Затем
    0.68
    T
    0.65
    P
    0.62
    ت
    0.62
    D
    0.61
    ה
    0.61
    H
    0.61
    המ
    0.61
    V
    0.61
    د
    0.60
    POSITIVE LOGITS
     they
    1.33
     it
    1.31
     there
    1.19
     despite
    1.06
     although
    1.06
     we
    1.04
     he
    0.95
    它
    0.95
     THEY
    0.93
     hey
    0.91
    Activations Density 0.080%

    No Known Activations