© 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. 64814
    Prev
    Next
    INDEX
    Explanations

    Bowl and Series championships

    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
     the
    -1.63
    昨晚
    -1.59
    ecco
    -1.55
    álna
    -1.51
    那时候
    -1.46
     étroite
    -1.46
     voelt
    -1.45
    formatics
    -1.45
     trám
    -1.45
     eſ
    -1.43
    POSITIVE LOGITS
     two
    1.25
     “
    1.22
    诧异
    1.20
    を持っている
    1.15
    ↵↵
    1.14
     préfère
    1.14
    mtliche
    1.13
    in
    1.12
    打量
    1.11
    级的
    1.09
    Activations Density 0.040%

    No Known Activations