© 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. 48697
    Prev
    Next
    INDEX
    Explanations

    measures and probability distributions

    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
    вного
    -0.89
     keskus
    -0.78
     利
    -0.76
     کامپی
    -0.74
     monotonic
    -0.73
    द्धि
    -0.72
    Stevens
    -0.72
    Meshes
    -0.71
     negation
    -0.71
    Cmp
    -0.69
    POSITIVE LOGITS
     measures
    1.18
    Measures
    1.02
     medidas
    1.00
     Measures
    0.98
     measure
    0.97
     concentrates
    0.91
    measures
    0.90
    support
    0.89
     distribution
    0.84
     меры
    0.83
    Activations Density 0.021%

    No Known Activations