© 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. 8520
    Prev
    Next
    INDEX
    Explanations

    updating information or software

    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
    м
    3.79
     véritable
    3.20
    ిక
    2.88
    SqlConnection
    2.85
    ल
    2.85
    te
    2.83
     Una
    2.80
     gracious
    2.71
    ور
    2.70
    好处
    2.63
    POSITIVE LOGITS
    ei
    2.80
    ္
    2.64
    мо
    2.63
    ્સ
    2.61
     Zeitung
    2.57
    namento
    2.55
    𝐥
    2.49
     mesi
    2.45
     частиц
    2.45
    ান্য
    2.44
    Activations Density 0.064%

    No Known Activations