© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66080
    Prev
    Next
    INDEX
    Explanations

    namespace/type definition

    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
     to
    -1.52
    licitations
    -1.20
    sqcup
    -1.15
    seats
    -1.14
    ckeye
    -1.13
     falleció
    -1.09
    ifornia
    -1.08
    着一个
    -1.08
    ivka
    -1.07
     Aunque
    -1.06
    POSITIVE LOGITS
     negozio
    1.27
    象徴
    1.20
     my
    1.17
    にしました
    1.17
     nastro
    1.16
     שלנו
    1.15
    effetto
    1.15
     murale
    1.13
     hábit
    1.11
     рассказывает
    1.10
    Activations Density 0.011%

    No Known Activations