© 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. 91405
    Prev
    Next
    INDEX
    Explanations

    electronics, humidifier, easier

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

    fallacy and relationship

    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
    ção
    0.52
     целей
    0.52
    ções
    0.49
     fom
    0.49
     Boley
    0.49
     corrigir
    0.46
    lement
    0.45
    嫵
    0.45
     известных
    0.45
     Autobiography
    0.45
    POSITIVE LOGITS
    хран
    0.49
    VariableName
    0.48
    itumor
    0.48
    甾
    0.47
    ੁ
    0.46
    ेशनल
    0.46
    त्सा
    0.46
    セックス
    0.45
    זר
    0.45
    Expires
    0.44
    Activations Density 0.000%

    No Known Activations