© 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. 213411
    Prev
    Next
    INDEX
    Explanations

    ideas to get

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

    prepare some

    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
     contributes
    0.48
     ornith
    0.46
     contributing
    0.44
     photons
    0.44
    ือบ
    0.42
    蟄
    0.42
    ॉट
    0.42
     cervix
    0.42
    缡
    0.42
    தைத்
    0.41
    POSITIVE LOGITS
    Dis
    0.43
    جو
    0.43
    rek
    0.41
     ස
    0.41
    to
    0.40
    JO
    0.40
     Cous
    0.40
    Jo
    0.40
     السوق
    0.40
    ශ
    0.39
    Activations Density 0.000%

    No Known Activations