© 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. 250470
    Prev
    Next
    INDEX
    Explanations

    states and periods

    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
    ାର
    0.41
    }
    0.41
     inflammatory
    0.39
     declaration
    0.38
     legislation
    0.38
    ！」
    0.38
    <0xE3>
    0.38
    ালি
    0.38
    </code>
    0.38
     fucking
    0.38
    POSITIVE LOGITS
     digamos
    0.43
     বনে
    0.42
     odby
    0.41
    🏺
    0.41
    डमी
    0.40
    .•
    0.40
     ,,
    0.40
    oltre
    0.40
     desh
    0.40
    educated
    0.40
    Activations Density 0.072%

    No Known Activations