© 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. 22-GEMMASCOPE-RES-131K
    7. 72378
    Prev
    Next
    INDEX
    Explanations

    geti, Million, idiom, demo, list

    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_22/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
     pincel
    -1.20
    Koordinaten
    -1.16
     stratég
    -1.12
     rám
    -1.10
     véhicule
    -1.10
    iç
    -1.08
    ủa
    -1.08
     становника
    -1.08
     manualidades
    -1.07
     bluza
    -1.07
    POSITIVE LOGITS
    2
    1.38
    a
    1.36
    d
    1.34
    e
    1.33
    y
    1.27
    8
    1.23
    is
    1.22
    z
    1.21
    1
    1.20
    th
    1.19
    Activations Density 0.023%

    No Known Activations