© 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. 34-GEMMASCOPE-RES-131K
    7. 108633
    Prev
    Next
    INDEX
    Explanations

    web form controls

    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
     poursuite
    -0.83
    olda
    -0.83
     emulsion
    -0.80
     agenda
    -0.77
    ิ้ง
    -0.75
    ƙ
    -0.75
     clicked
    -0.73
    فحة
    -0.72
     digestible
    -0.72
     séparation
    -0.71
    POSITIVE LOGITS
    input
    1.13
     input
    1.05
    controls
    1.02
    radio
    0.98
     satisfying
    0.94
     controls
    0.88
    InputGroup
    0.82
    Controls
    0.81
     compacto
    0.80
     help
    0.79
    Activations Density 0.009%

    No Known Activations