© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130407
    Prev
    Next
    INDEX
    Explanations

    your room

    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
    ּוֹ
    -1.16
    ֶּ
    -1.11
    完成です
    -1.02
    }){
    -0.93
    还好
    -0.90
     avendo
    -0.88
    angerie
    -0.88
    olucion
    -0.86
     Ә
    -0.85
    ִּ
    -0.84
    POSITIVE LOGITS
     your
    1.44
     already
    1.41
     otherwise
    1.16
     especially
    1.15
     any
    1.13
     już
    1.06
    分ほど
    1.03
     tatuagens
    1.02
    Already
    1.02
    СТВО
    1.02
    Activations Density 0.027%

    No Known Activations