© 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. 226772
    Prev
    Next
    INDEX
    Explanations

    survival background inquiries parts

    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
     litigants
    0.44
    essages
    0.44
     রাম
    0.43
     Sloane
    0.43
    Buenas
    0.41
     ఎమ్మెల్యే
    0.41
    丁寧に
    0.40
    生徒
    0.40
    ኮ
    0.40
     هار
    0.39
    POSITIVE LOGITS
     எரி
    0.52
    所以在
    0.45
     euismod
    0.44
     пови
    0.43
     Maintains
    0.43
     altera
    0.42
     அறை
    0.42
    ного
    0.42
     авгу
    0.41
    矛盾
    0.41
    Activations Density 0.002%

    No Known Activations