© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107285
    Prev
    Next
    INDEX
    Explanations

    support and help

    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
    isiin
    -0.87
     escla
    -0.84
    Salz
    -0.79
    gliere
    -0.78
    oodles
    -0.77
    шеб
    -0.77
     Abbiamo
    -0.77
    melding
    -0.77
    Panzer
    -0.77
    eficiente
    -0.77
    POSITIVE LOGITS
     support
    7.53
    support
    5.78
     supports
    5.28
    支持
    5.25
    Support
    5.25
     supporting
    4.88
    SUPPORT
    4.88
     SUPPORT
    4.84
     Support
    4.84
     supported
    4.63
    Activations Density 0.142%

    No Known Activations