© 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. 33623
    Prev
    Next
    INDEX
    Explanations

    Manny Puig

    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
     of
    -1.26
    ≅
    -1.23
    multirow
    -1.17
    ∅
    -1.16
     soos
    -1.09
    brad
    -1.07
     its
    -1.07
    IElement
    -1.05
     złot
    -1.05
    Û
    -1.02
    POSITIVE LOGITS
     these
    1.32
    做过
    1.21
    這些
    1.21
     reunião
    1.15
     täglichen
    1.13
     releases
    1.10
    écart
    1.10
    諄
    1.06
    habitude
    1.04
     wesentlichen
    1.03
    Activations Density 0.003%

    No Known Activations