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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4083
    Prev
    Next
    INDEX
    Explanations

    private

    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_29_width_65k_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
    ześ
    0.66
     નિર્
    0.65
    ಡಿ
    0.64
     যানবাহন
    0.60
    ികള
    0.59
    නා
    0.58
     Ingersoll
    0.58
    杯
    0.58
    ulang
    0.57
    वर्स
    0.57
    POSITIVE LOGITS
     private
    5.72
    Private
    5.25
    private
    5.24
     Private
    5.18
     PRIVATE
    4.74
    PRIVATE
    4.39
     privado
    4.37
     privato
    4.37
     privata
    4.31
    私
    4.24
    Activations Density 0.400%

    No Known Activations