© 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. 34-GEMMASCOPE-RES-131K
    7. 12220
    Prev
    Next
    INDEX
    Explanations

    enum definitions and headings like News, Along, Q

    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_34/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
     (
    -1.34
     additional
    -1.18
     it
    -1.12
     our
    -1.04
     then
    -1.03
     will
    -0.98
    additional
    -0.95
     this
    -0.91
     feel
    -0.90
     +
    -0.88
    POSITIVE LOGITS
     NONE
    1.38
     none
    1.36
     None
    1.20
    None
    1.15
     '/';
    1.12
     UNKNOWN
    1.10
    ,;
    1.05
     枚
    1.05
     Unknown
    1.04
     desconocido
    1.03
    Activations Density 0.016%

    No Known Activations