© 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. 14278
    Prev
    Next
    INDEX
    Explanations

    start of HTML document

    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
    নের
    0.87
    screens
    0.84
    藝
    0.77
    said
    0.73
    summon
    0.73
     resemblance
    0.72
    ¿
    0.72
    made
    0.72
    regated
    0.71
    বৃত্ত
    0.70
    POSITIVE LOGITS
    aviti
    1.21
     contas
    1.05
    isle
    1.03
     Volcano
    1.01
    ٖ
    0.99
     Datuk
    0.97
    icula
    0.95
     মেজর
    0.95
    دانلود
    0.94
    rVert
    0.94
    Activations Density 0.002%

    No Known Activations