© 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. 15087
    Prev
    Next
    INDEX
    Explanations

    async or delayed execution

    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
     nieuwe
    -1.29
     aksesuar
    -1.16
    Ꮬ
    -1.14
     laſt
    -1.11
     !!!!!
    -1.11
    艫
    -1.07
     koltuk
    -1.06
    Réponse
    -1.06
    👛
    -1.06
     様子
    -1.05
    POSITIVE LOGITS
     (
    1.59
    (
    1.36
    It
    1.28
     after
    1.13
    （
    1.10
     it
    1.06
    !
    1.05
     undeniably
    1.02
    In
    1.02
     at
    1.02
    Activations Density 0.004%

    No Known Activations