© 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. 29-GEMMASCOPE-2-RES-262K
    7. 145594
    Prev
    Next
    INDEX
    Explanations

    evocative nouns

    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
    Negative Logits
     guys
    0.69
     vaikka
    0.66
     Worse
    0.65
    </em>
    0.64
    FAILED
    0.64
     deren
    0.63
    because
    0.63
    俩
    0.62
     rubble
    0.62
     बहुतेक
    0.62
    POSITIVE LOGITS
     soft
    0.99
    <start_of_image>
    0.99
    inia
    0.90
     léger
    0.89
     légère
    0.89
    soft
    0.88
    Soft
    0.86
     reaching
    0.86
     compreender
    0.84
     definición
    0.84
    Activations Density 0.060%

    No Known Activations