© 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. 16126
    Prev
    Next
    INDEX
    Explanations

    code entities and phrases

    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
     emblema
    -1.38
    ～！
    -1.38
     on
    -1.38
     equipe
    -1.34
     with
    -1.29
    🕗
    -1.25
    createNewFile
    -1.23
     at
    -1.23
     digunakan
    -1.22
     latas
    -1.21
    POSITIVE LOGITS
    _
    1.26
    le
    1.26
    んでも
    1.25
    b
    1.25
    u
    1.23
    z
    1.22
     alcune
    1.17
     geliefert
    1.16
    際には
    1.16
     liegenden
    1.16
    Activations Density 0.004%

    No Known Activations