© 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. 77793
    Prev
    Next
    INDEX
    Explanations

    animated properties and 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
     trajo
    -0.85
    veras
    -0.82
    Nosotros
    -0.82
    жение
    -0.79
    ɵɵelementStart
    -0.78
    kovi
    -0.76
    harmonie
    -0.76
     upside
    -0.76
    makeConstraints
    -0.75
    암
    -0.75
    POSITIVE LOGITS
     opacity
    1.20
     volume
    1.14
    volume
    1.13
    opacity
    1.13
     volumes
    0.99
     VOLUME
    0.90
     turbidity
    0.82
    Volume
    0.82
    recur
    0.81
    queue
    0.79
    Activations Density 0.006%

    No Known Activations