© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181737
    Prev
    Next
    INDEX
    Explanations

    computer virus and environmental improvement

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

    starfish limb, time, difficult, software

    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
     tend
    0.46
    ierung
    0.45
    };
    0.45
    }((
    0.45
    施術
    0.44
    调整
    0.44
    omain
    0.44
    ேட்
    0.43
    coordinate
    0.43
    ли
    0.43
    POSITIVE LOGITS
    ני
    0.47
     spoon
    0.46
     electronic
    0.45
     DELETE
    0.43
     électronique
    0.42
     expired
    0.42
    숟
    0.42
    奭
    0.42
     encouragement
    0.42
     எல்லாம்
    0.41
    Activations Density 0.001%

    No Known Activations