© 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. 10-GEMMASCOPE-RES-131K
    7. 128692
    Prev
    Next
    INDEX
    Explanations

    conditional checks

    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
    ꜆
    -1.80
     можуть
    -1.75
     могут
    -1.64
     mogą
    -1.38
     โดย
    -1.35
     extrême
    -1.34
     possono
    -1.33
     spesso
    -1.32
    </h4>
    -1.29
    
    -1.27
    POSITIVE LOGITS
     if
    1.35
     in
    1.34
     for
    1.32
     will
    1.28
     of
    1.23
    kenal
    1.18
     or
    1.16
    :
    1.14
     zorgt
    1.12
    ÍTICA
    1.12
    Activations Density 0.002%

    No Known Activations