© 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. 16571
    Prev
    Next
    INDEX
    Explanations

    transition from

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

    noticing expect potentially

    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
     অত্যা
    0.44
     olika
    0.44
     carbs
    0.43
    大大
    0.43
    怆
    0.43
     резко
    0.42
    categ
    0.42
    我自己
    0.41
    তাকে
    0.41
     plates
    0.41
    POSITIVE LOGITS
    Результа
    0.44
     причине
    0.43
    sortie
    0.42
     रखने
    0.42
    ერი
    0.41
     बढ़ोतरी
    0.41
     നടത്തിയ
    0.40
    ⬤
    0.40
     professeur
    0.39
    GK
    0.39
    Activations Density 0.000%

    No Known Activations