© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9536
    Prev
    Next
    INDEX
    Explanations

    agency or organization

    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
     dzien
    2.68
    ф
    2.65
    ান
    2.62
    য়ের
    2.55
     boton
    2.47
    פ
    2.43
    ands
    2.42
     дру
    2.38
     telas
    2.37
    ड
    2.33
    POSITIVE LOGITS
    瘩
    3.20
    ally
    3.06
    RMSE
    2.79
    sthe
    2.78
    м
    2.78
    ال
    2.74
    ความ
    2.74
    어야
    2.73
     desee
    2.72
    ה
    2.71
    Activations Density 0.138%

    No Known Activations