© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93295
    Prev
    Next
    INDEX
    Explanations

    in the meantime

    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_22/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
     later
    -1.48
    hnout
    -1.23
     kiedyś
    -1.17
     then
    -1.15
    ˼
    -1.14
     successivamente
    -1.13
     nantinya
    -1.13
    eventually
    -1.09
     없
    -1.06
    Sonntag
    -1.05
    POSITIVE LOGITS
     enjoy
    1.53
     continue
    1.48
    .”
    1.16
     lieber
    1.09
     tecnológicos
    1.07
     let
    1.05
     remain
    1.04
     продолжа
    1.02
     keep
    0.97
     please
    0.96
    Activations Density 0.012%

    No Known Activations