© 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. 166565
    Prev
    Next
    INDEX
    Explanations

    details or items mentioned individually

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

    using butter

    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
    ស្
    0.53
    աբ
    0.47
    вор
    0.47
    iat
    0.46
    }',
    0.45
    كنولوج
    0.45
    ар
    0.44
    }());
    0.44
    CRET
    0.44
    }",
    0.43
    POSITIVE LOGITS
     Rouge
    0.55
     Bleu
    0.50
     Audiobook
    0.50
     código
    0.49
     Otter
    0.49
     Lambda
    0.49
     Hospice
    0.48
     audiobook
    0.48
     rouge
    0.48
     Twelve
    0.48
    Activations Density 0.000%

    No Known Activations