© 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. 65024
    Prev
    Next
    INDEX
    Explanations

    not saying

    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
    デカ
    -1.19
     plutôt
    -1.14
     både
    -1.11
     égard
    -1.09
     fuis
    -1.08
     rather
    -1.06
     genoux
    -1.05
    罍
    -1.05
    カビ
    -1.03
     camiset
    -1.02
    POSITIVE LOGITS
     any
    1.84
     necessarily
    1.77
    有任何
    1.37
     ever
    1.29
     anything
    1.28
     over
    1.26
     anymore
    1.26
     EVER
    1.17
     even
    1.16
    necessarily
    1.16
    Activations Density 0.061%

    No Known Activations