© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185665
    Prev
    Next
    INDEX
    Explanations

    autistic younger

    np_acts-logits-general · gemini-2.5-flash-lite

    explaining different approaches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     asphalt
    0.52
    améli
    0.49
     (++
    0.47
     miglior
    0.45
    ́i
    0.45
    amélioration
    0.45
    이트
    0.44
    isetas
    0.44
     było
    0.44
     برانيه
    0.43
    POSITIVE LOGITS
    ya
    0.45
     לע
    0.44
    ka
    0.42
     একইভাবে
    0.42
     Judas
    0.41
    とき
    0.40
    haw
    0.40
    𝘢
    0.40
    det
    0.40
    🔸
    0.39
    Activations Density 0.000%

    No Known Activations