© 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. 9546
    Prev
    Next
    INDEX
    Explanations

    FranceFrench

    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
    ל
    3.33
    ت
    2.97
    пати
    2.46
     annular
    2.43
    \{
    2.41
     sorte
    2.40
    сл
    2.40
     İlk
    2.39
     annulus
    2.39
     rov
    2.36
    POSITIVE LOGITS
    دة
    3.09
     ActiveRecord
    2.96
    nge
    2.92
    ं
    2.78
    p
    2.78
    éd
    2.76
    ée
    2.75
     {...
    2.75
    তে
    2.73
    nelle
    2.68
    Activations Density 0.134%

    No Known Activations