© 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. 64725
    Prev
    Next
    INDEX
    Explanations

    your or phrase

    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
     four
    -1.45
     nine
    -1.37
     necessary
    -1.37
     температур
    -1.36
     eight
    -1.32
     الوزراء
    -1.31
     this
    -1.30
     varied
    -1.29
     five
    -1.28
     three
    -1.21
    POSITIVE LOGITS
     you
    2.20
     شما
    1.60
     montrant
    1.55
     évé
    1.52
    viewDid
    1.45
     réguli
    1.41
     rémun
    1.41
     prédé
    1.39
     your
    1.38
     kanker
    1.36
    Activations Density 0.023%

    No Known Activations