© 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. 65540
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     will
    -1.36
     whose
    -1.35
    ampilkan
    -1.22
     岁
    -1.21
     seconda
    -1.19
     Despite
    -1.17
     after
    -1.15
    ということです
    -1.14
     should
    -1.12
    视着
    -1.11
    POSITIVE LOGITS
    。
    1.22
     the
    1.14
     wektor
    1.09
     maravill
    1.06
    ."
    1.03
     такой
    1.02
     hermosos
    1.02
    grats
    1.02
     beautifully
    1.01
    yamaha
    1.01
    Activations Density 0.040%

    No Known Activations