© 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. 15859
    Prev
    Next
    INDEX
    Explanations

    you can/should/may

    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
     then
    -1.25
     by
    -1.16
     Want
    -1.14
     neuen
    -1.14
     Some
    -1.13
    ₓ
    -1.07
     Many
    -1.07
     using
    -1.06
     However
    -1.06
     With
    -1.01
    POSITIVE LOGITS
     nejen
    1.25
     weder
    1.22
     môže
    1.20
    actually
    1.16
     realmente
    1.16
     spôso
    1.15
     neither
    1.15
     môžete
    1.13
    Linkedin
    1.13
     tohto
    1.13
    Activations Density 0.019%

    No Known Activations