© 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. 146522
    Prev
    Next
    INDEX
    Explanations

    @returns documentation

    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
    infra
    0.75
     infra
    0.72
    inheritdoc
    0.69
    back
    0.67
    return
    0.67
    ''}
    0.66
    unfair
    0.63
    larger
    0.63
    german
    0.62
    larghezza
    0.62
    POSITIVE LOGITS
     Spectra
    0.87
    তুল
    0.80
     atmosphere
    0.76
     ब्लड
    0.76
     Lucille
    0.76
    =*
    0.75
     splitting
    0.74
     Stakes
    0.73
     Which
    0.73
     Extreme
    0.73
    Activations Density 0.001%

    No Known Activations