© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34949
    Prev
    Next
    INDEX
    Explanations

    emphatic statements and punctuation

    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
     but
    -1.85
    찮
    -1.45
     then
    -1.34
     for
    -1.23
     will
    -1.23
     хорошее
    -1.20
     непло
    -1.20
     m
    -1.14
     однако
    -1.14
    getNombre
    -1.13
    POSITIVE LOGITS
    ICULO
    1.43
     ませ
    1.40
     навіть
    1.40
     every
    1.37
     absolument
    1.36
     thậm
    1.35
     pratiquement
    1.32
     addirittura
    1.29
     حتی
    1.28
     Кроме
    1.27
    Activations Density 0.016%

    No Known Activations