© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103087
    Prev
    Next
    INDEX
    Explanations

    words starting with re

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     which
    -2.97
     when
    -2.64
     of
    -2.63
     where
    -2.63
     Since
    -2.45
     that
    -2.44
     what
    -2.33
     as
    -2.33
     because
    -2.23
     who
    -2.22
    POSITIVE LOGITS
     offre
    2.20
     поиска
    2.19
     différent
    2.17
    ༔
    2.11
    ౬
    2.09
    臯
    2.08
    顔を
    2.08
     VERY
    2.06
    还想
    2.06
     ridiculously
    2.03
    Activations Density 0.080%

    No Known Activations