© 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. 8719
    Prev
    Next
    INDEX
    Explanations

    small amount or degree

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

    slightly

    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
     TARGET
    0.40
     ITER
    0.39
     banyak
    0.38
     needless
    0.38
     TIMES
    0.38
     ternyata
    0.38
    !
    0.38
     !
    0.37
     TIME
    0.37
    <unused81>
    0.37
    POSITIVE LOGITS
     mildly
    0.71
     약간
    0.60
     glimpse
    0.59
     немного
    0.56
     మాత్రమే
    0.56
    而已
    0.55
     слегка
    0.54
    有一些
    0.53
    slightly
    0.53
     beetje
    0.52
    Activations Density 0.359%

    No Known Activations