© 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. 34361
    Prev
    Next
    INDEX
    Explanations

    first name followed by initial or surname

    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
     soldat
    -1.34
     carcasa
    -1.32
     restaurantes
    -1.32
     silueta
    -1.29
     ralla
    -1.26
     batteri
    -1.25
     voyageurs
    -1.23
    Ɣ
    -1.22
     vieux
    -1.21
     mobilier
    -1.21
    POSITIVE LOGITS
     estaremos
    1.18
     who
    1.14
    //!
    1.10
     in
    1.09
     They
    1.09
    shadowColor
    1.05
     because
    1.05
     from
    1.04
     ļoti
    1.04
     And
    1.01
    Activations Density 0.044%

    No Known Activations