© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11428
    Prev
    Next
    INDEX
    Explanations

    actions and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ungkinkan
    0.49
     spos
    0.47
    ţii
    0.47
     των
    0.47
    ۲
    0.46
     have
    0.46
    வேன்
    0.46
     ﺍﻟ
    0.46
     occasioned
    0.44
     කිරීමට
    0.44
    POSITIVE LOGITS
     Freak
    0.39
     Guerra
    0.39
    его
    0.39
    法的
    0.38
    <0x82>
    0.37
     Theoretically
    0.37
     Actors
    0.37
    Glam
    0.37
    Actors
    0.36
    ಲ್ಲ
    0.36
    Activations Density 0.182%

    No Known Activations