© 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. 83610
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

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

    time or history

    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
    情绪
    0.53
     eterno
    0.50
     eternally
    0.46
    恻
    0.46
    ोग्राम
    0.45
    放弃
    0.44
    黉
    0.44
     irrevoc
    0.44
     blindly
    0.44
     unconditionally
    0.43
    POSITIVE LOGITS
    a
    0.56
     τ
    0.54
    resistant
    0.54
     ت
    0.53
     t
    0.52
    soph
    0.52
    8
    0.52
    3
    0.51
     δ
    0.50
    austral
    0.50
    Activations Density 0.000%

    No Known Activations