© 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. 108678
    Prev
    Next
    INDEX
    Explanations

    GADGET-2, ray-tracing, application, divide, Effects

    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
     Masonic
    -0.82
     Elementary
    -0.72
    Elementary
    -0.71
     міся
    -0.70
    定休日
    -0.68
    校验
    -0.68
    Niels
    -0.68
     epile
    -0.67
    tipp
    -0.67
     Erkrank
    -0.66
    POSITIVE LOGITS
     gadget
    1.13
     GAD
    0.99
    gadget
    0.95
     softening
    0.88
    GAD
    0.87
    Gadget
    0.87
     particles
    0.87
     particle
    0.86
     snapshots
    0.85
    /*!
    0.84
    Activations Density 0.015%

    No Known Activations