© 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. 65613
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
     your
    -0.97
     regarding
    -0.93
     While
    -0.92
     an
    -0.88
     then
    -0.85
     Aside
    -0.84
     Before
    -0.83
     epitom
    -0.82
     attempting
    -0.82
     which
    -0.82
    POSITIVE LOGITS
    each
    1.02
    ⇐
    1.00
    MING
    0.99
    Its
    0.98
    Email
    0.98
    always
    0.97
    ruhe
    0.97
    Feel
    0.96
     echa
    0.95
     toujours
    0.95
    Activations Density 0.018%

    No Known Activations