© 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. 250665
    Prev
    Next
    INDEX
    Explanations

    objectives and builder

    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
    Not in Any Lists

    No Comments

    Negative Logits
     کوشش
    0.49
     dancers
    0.48
     estimators
    0.47
    ᙱ
    0.47
     nymph
    0.46
     foragers
    0.46
     théra
    0.46
    掟
    0.45
    loose
    0.45
    ⵡ
    0.45
    POSITIVE LOGITS
    ereo
    0.47
    펜
    0.45
    ాడు
    0.45
    imentos
    0.45
    ാ
    0.45
     Macintosh
    0.44
     Cumhuriyet
    0.44
     Mald
    0.43
     Buenos
    0.42
    HttpMessage
    0.42
    Activations Density 0.000%

    No Known Activations