© 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. 68460
    Prev
    Next
    INDEX
    Explanations

    specific words followed by another

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

    actions and concepts

    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
     Titles
    0.45
    illae
    0.43
     lessened
    0.42
    Kö
    0.42
    increased
    0.41
     differs
    0.40
    {}".
    0.40
    RPM
    0.40
    萌
    0.40
     isotope
    0.40
    POSITIVE LOGITS
    ۴
    0.50
    гора
    0.49
    ग्राम
    0.48
    фессиона
    0.48
     chairmanship
    0.48
    전히
    0.47
     అధ్యక్ష
    0.47
     Bienvenidos
    0.46
    setDefault
    0.46
     अनार
    0.46
    Activations Density 0.000%

    No Known Activations