© 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. 88352
    Prev
    Next
    INDEX
    Explanations

    et al

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

    AI chatbot interaction

    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
    家里
    0.53
     animator
    0.50
     komplette
    0.48
    美丽的
    0.47
    栘
    0.47
     संश्
    0.46
    看不到
    0.46
    樖
    0.45
    住宅
    0.45
     variously
    0.44
    POSITIVE LOGITS
    0.54
     Meaning
    0.52
     meaning
    0.48
     Disbursement
    0.45
     Thus
    0.45
    ↵↵
    0.44
    __
    0.44
     Without
    0.44
     Ticket
    0.44
     /
    0.44
    Activations Density 0.000%

    No Known Activations