© 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. 68068
    Prev
    Next
    INDEX
    Explanations

    explaining unexpectedness

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

    somehow followed by consequence

    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
    ش
    0.55
    ן
    0.52
    tone
    0.51
    ιος
    0.48
     actually
    0.48
     congruent
    0.48
    ն
    0.47
     seasoned
    0.46
    зка
    0.45
     storytelling
    0.43
    POSITIVE LOGITS
     Somehow
    0.82
     somehow
    0.55
     ८
    0.50
    वश
    0.50
     inexplic
    0.48
    brellas
    0.47
    arantad
    0.46
    どうしても
    0.46
    apagos
    0.45
    atos
    0.45
    Activations Density 0.043%

    No Known Activations