© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 10710
    Prev
    Next
    INDEX
    Explanations

    code examples (python, bash, json)

    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_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     archiving
    0.82
    .").
    0.79
    ."),
    0.76
     breaking
    0.75
     blending
    0.75
     perceptions
    0.75
     Ç
    0.75
    €™
    0.75
     regulating
    0.75
     excellence
    0.74
    POSITIVE LOGITS
    ↵
    1.30
    esempio
    1.10
    Example
    1.10
    Picker
    1.05
    example
    1.00
    exemple
    1.00
     exemple
    0.98
    Pick
    0.96
    bash
    0.95
    ׃
    0.93
    Activations Density 0.113%

    No Known Activations