© 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. 22412
    Prev
    Next
    INDEX
    Explanations

    and other/these

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

    connecting clauses with "and"

    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
     کی۔
    0.63
    +.
    0.55
    ™.
    0.54
    。
    0.54
    ।...
    0.54
    *.
    0.53
    %。
    0.52
    。《
    0.52
    ®.
    0.50
    ³.
    0.50
    POSITIVE LOGITS
     are
    0.76
    人都
    0.71
     jsou
    0.64
    我都
    0.63
     were
    0.61
     ovat
    0.58
     sont
    0.58
     هستند
    0.56
     saranno
    0.56
    都會
    0.56
    Activations Density 0.266%

    No Known Activations