© 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. 1908
    Prev
    Next
    INDEX
    Explanations

    Fraunhofer Line Depth

    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
    valry
    -0.78
    snapshots
    -0.77
    kete
    -0.74
    輿
    -0.73
    我了
    -0.72
    ابس
    -0.72
     Olin
    -0.71
     Cyclone
    -0.71
    racy
    -0.69
     COMMAND
    -0.69
    POSITIVE LOGITS
     aerosol
    1.04
     solar
    0.94
     sun
    0.94
     retrieved
    0.89
    jacency
    0.84
     sza
    0.84
     sky
    0.83
     aerosols
    0.82
     Sun
    0.82
     radiance
    0.82
    Activations Density 0.018%

    No Known Activations