© 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. 5816
    Prev
    Next
    INDEX
    Explanations

    what would questions

    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
     arbeitet
    0.88
     që
    0.84
    évő
    0.83
     こと
    0.83
     gì
    0.82
     vais
    0.82
     cleft
    0.82
    ҥ
    0.82
    Believe
    0.81
     sendiri
    0.81
    POSITIVE LOGITS
     be
    0.92
     their
    0.90
     convincing
    0.87
    their
    0.83
     motivating
    0.81
     our
    0.79
    top
    0.77
     persuading
    0.74
     realistic
    0.73
     Their
    0.72
    Activations Density 0.034%

    No Known Activations