© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146810
    Prev
    Next
    INDEX
    Explanations

    unit test cases

    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_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
    પ
    0.91
     প
    0.84
     plist
    0.81
     पड
    0.81
     פ
    0.78
    പേ
    0.77
     nh
    0.75
    સે
    0.75
     Rada
    0.75
     Mode
    0.75
    POSITIVE LOGITS
    ︽
    0.87
    holds
    0.85
    criminals
    0.83
    call
    0.80
    Lyrics
    0.77
    calls
    0.77
     gören
    0.75
    frontal
    0.75
    givers
    0.75
    script
    0.74
    Activations Density 0.000%

    No Known Activations