© 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. 72952
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
    Wszyst
    -1.02
     absolue
    -0.95
     milagro
    -0.95
     tumba
    -0.95
     adorno
    -0.91
     rosas
    -0.88
     warszawa
    -0.88
     avenida
    -0.88
     it
    -0.87
    DatePicker
    -0.87
    POSITIVE LOGITS
     ____________
    1.08
    ôs
    1.07
    −/−
    1.05
    orithmic
    0.99
    neling
    0.98
     जिन
    0.96
     mentre
    0.96
     для
    0.95
     другому
    0.93
    OSS
    0.93
    Activations Density 0.011%

    No Known Activations