© 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. 37749
    Prev
    Next
    INDEX
    Explanations

    cars, ox, pet

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

    distinct entities, RPG, various styles

    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
     দশকের
    0.55
     সভাপতিত্ব
    0.47
    ü
    0.47
     ।,
    0.47
     terletak
    0.46
    itabbo
    0.45
     වෙත
    0.45
     auspices
    0.45
    ënten
    0.44
     झा
    0.44
    POSITIVE LOGITS
     Hilary
    0.48
     Murad
    0.46
     Eduard
    0.46
     Harman
    0.46
     Rodrigo
    0.44
    мий
    0.44
    ковий
    0.44
    س
    0.44
    ﺪ
    0.44
    кому
    0.43
    Activations Density 0.002%

    No Known Activations