© 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. 8163
    Prev
    Next
    INDEX
    Explanations

    life, law, club, man, team

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

    AI assistant

    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
     அல்லது
    0.43
     ឬ
    0.40
    あるいは
    0.39
     hoặc
    0.38
     eller
    0.38
     或
    0.38
     maupun
    0.38
     või
    0.38
     ಅಥವಾ
    0.36
     ataupun
    0.35
    POSITIVE LOGITS
    잖아요
    0.44
    잖아
    0.42
    あくまで
    0.39
     pertenc
    0.39
    ല്ലോ
    0.38
    毕竟
    0.37
     meant
    0.37
    ですから
    0.35
    ♰
    0.35
     fundamentally
    0.35
    Activations Density 0.387%

    No Known Activations