© 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. 29-GEMMASCOPE-2-RES-65K
    7. 4660
    Prev
    Next
    INDEX
    Explanations

    Shifting

    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
     पाते
    0.81
     Modification
    0.80
    媲
    0.77
    iejęt
    0.75
     pasada
    0.75
     нулю
    0.75
    以前
    0.75
    ------------*/
    0.75
    metic
    0.72
     disparo
    0.72
    POSITIVE LOGITS
     Sh
    1.23
     sh
    1.16
    Sh
    1.03
    sh
    0.82
     SH
    0.72
     ஷ
    0.72
    SH
    0.65
    antung
    0.64
     الش
    0.64
    ining
    0.63
    Activations Density 0.028%

    No Known Activations