© 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. 48723
    Prev
    Next
    INDEX
    Explanations

    wireless adapter or data

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

    tailor, inference, significant changes, unusual patterns, determined actions, aggression, advanced AI, metaphorical sense

    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
    ма
    0.54
    oqu
    0.49
     Fork
    0.46
    ума
    0.46
    с
    0.46
     व्यू
    0.45
     hectic
    0.45
     fork
    0.45
     feet
    0.44
     cherries
    0.44
    POSITIVE LOGITS
    őtt
    0.50
    ל
    0.46
    ragen
    0.44
     Toutes
    0.43
     électronique
    0.43
     לס
    0.43
     szeret
    0.43
     fejleszt
    0.42
    㕶
    0.42
    lett
    0.42
    Activations Density 0.000%

    No Known Activations