© 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. 65783
    Prev
    Next
    INDEX
    Explanations

    mathematical or technical notation

    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
    ittäin
    -1.21
    ITER
    -1.13
    decided
    -1.12
     Mise
    -1.11
    analyser
    -1.09
    identified
    -1.09
    pelier
    -1.08
     THER
    -1.07
     córdoba
    -1.05
     wenigstens
    -1.04
    POSITIVE LOGITS
     it
    1.31
     for
    1.20
     Weiterbildung
    1.16
     we
    1.13
    丁目
    1.11
    getLabel
    1.11
     with
    1.09
     or
    1.09
    openha
    1.09
     you
    1.09
    Activations Density 0.025%

    No Known Activations