© 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. 429
    Prev
    Next
    INDEX
    Explanations

    can happen

    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
     Accordingly
    0.74
    Accordingly
    0.74
     court
    0.72
    But
    0.71
    所以在
    0.66
     enfim
    0.65
    :]
    0.64
    :],
    0.64
     But
    0.64
    Consequently
    0.63
    POSITIVE LOGITS
     бушлай
    0.97
     QSOs
    0.95
    undred
    0.89
     Ј
    0.89
    äller
    0.88
     keine
    0.87
    ISTRATION
    0.85
    érapie
    0.85
     каттоосуз
    0.85
    ₱
    0.85
    Activations Density 0.000%

    No Known Activations