© 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. 5992
    Prev
    Next
    INDEX
    Explanations

    ways to use things

    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
    expensive
    0.65
     लायक
    0.63
    Vale
    0.62
    Fantastic
    0.61
    Rot
    0.59
    ิด
    0.58
    fantastic
    0.56
    experiment
    0.56
    Expensive
    0.56
    셈
    0.56
    POSITIVE LOGITS
     Ways
    0.80
     ways
    0.79
    gios
    0.78
     desks
    0.78
     utilises
    0.78
     способов
    0.77
     utilisation
    0.75
    用法
    0.74
    getEstado
    0.73
     máte
    0.73
    Activations Density 0.000%

    No Known Activations