© 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. 174997
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

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

    values across

    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
    tober
    0.51
    s
    0.49
    ভারতীয়
    0.48
     Derbyshire
    0.47
    went
    0.47
     went
    0.45
     le
    0.45
     Rajput
    0.45
     Went
    0.45
     Desai
    0.44
    POSITIVE LOGITS
    其它
    0.52
    职责
    0.48
    焦虑
    0.47
    袜子
    0.46
    互相
    0.46
    笼
    0.46
     élargies
    0.44
    更有
    0.43
    模糊
    0.43
    岁月
    0.43
    Activations Density 0.001%

    No Known Activations