© 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. 34-GEMMASCOPE-RES-131K
    7. 31140
    Prev
    Next
    INDEX
    Explanations

    configuration and control options

    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
    お待ちしております
    -0.91
    が含ま
    -0.90
    ghted
    -0.90
    Includes
    -0.88
    에서는
    -0.86
    Suitable
    -0.84
    includes
    -0.83
     SHOWS
    -0.83
     nuestros
    -0.82
    今年の
    -0.80
    POSITIVE LOGITS
     controlling
    1.77
    控制
    1.77
     control
    1.72
    controlling
    1.63
     controls
    1.63
     Controlling
    1.57
     influence
    1.53
     controlled
    1.49
    影响
    1.41
    Controlling
    1.40
    Activations Density 0.127%

    No Known Activations