© 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. 22-GEMMASCOPE-2-RES-262K
    7. 3452
    Prev
    Next
    INDEX
    Explanations

    code elements

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ;)
    0.86
    ;")
    0.79
    ቃል
    0.78
     بنائیں
    0.73
    ;;)
    0.71
    :')
    0.69
    ;')
    0.69
    ራል
    0.68
     shrunk
    0.66
     relationship
    0.66
    POSITIVE LOGITS
    ().
    2.78
    }.
    2.10
    _.
    2.08
     ().
    2.02
    ".
    1.96
    .).
    1.93
    ₁.
    1.93
    $.
    1.92
    ('/').
    1.92
    ™.
    1.92
    Activations Density 0.204%

    No Known Activations