© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129328
    Prev
    Next
    INDEX
    Explanations

    relationship with

    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
     început
    -1.71
     jednoduch
    -1.64
    </em>
    -1.63
     dobré
    -1.54
     guapos
    -1.48
    ～！
    -1.48
     utilisons
    -1.44
    
    -1.40
     jiné
    -1.40
     všechny
    -1.40
    POSITIVE LOGITS
     its
    1.81
     these
    1.77
     our
    1.77
     of
    1.77
     each
    1.67
     Dijo
    1.58
     both
    1.52
     Pueden
    1.51
     Algunas
    1.48
     this
    1.47
    Activations Density 0.026%

    No Known Activations