© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73003
    Prev
    Next
    INDEX
    Explanations

    code structure 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_10/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
     a
    -1.38
     homicidio
    -1.27
     from
    -1.25
    ;
    -1.23
     soggiorno
    -1.16
     Gegenteil
    -1.16
     an
    -1.16
     October
    -1.14
     Alternative
    -1.14
     lainnya
    -1.13
    POSITIVE LOGITS
    ???:
    1.30
    ensiva
    1.24
     biodivers
    1.23
    cipar
    1.23
    ellants
    1.23
     BORN
    1.23
    **
    1.22
    💔
    1.21
    utando
    1.21
     Garantie
    1.20
    Activations Density 0.020%

    No Known Activations