© 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. 9-GEMMASCOPE-2-RES-262K
    7. 8566
    Prev
    Next
    INDEX
    Explanations

    exit followed by parentheses

    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_9_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
     NPR
    2.82
    اته
    2.72
    mata
    2.70
    en
    2.66
    ת
    2.60
    त
    2.59
     parton
    2.57
    ahraga
    2.56
    hopping
    2.54
    <unused35>
    2.54
    POSITIVE LOGITS
    फारिश
    3.17
     diagonalizable
    2.79
    ב
    2.66
     समझौता
    2.59
    ▬▬
    2.56
    আন্ত
    2.53
     kra
    2.52
    дя
    2.50
    impresa
    2.49
    imize
    2.47
    Activations Density 0.006%

    No Known Activations