© 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. 3910
    Prev
    Next
    INDEX
    Explanations

    Key explanations

    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
     Inspection
    0.72
     derail
    0.69
     unset
    0.64
    侓
    0.63
     Division
    0.63
     Divided
    0.62
    oline
    0.62
     inspections
    0.62
    ौली
    0.61
     Sna
    0.60
    POSITIVE LOGITS
    кей
    0.76
    kej
    0.75
    袈
    0.73
    кий
    0.73
     kock
    0.71
    kata
    0.71
    gloss
    0.70
     लिहा
    0.69
     העולם
    0.68
    itiis
    0.68
    Activations Density 0.026%

    No Known Activations