© 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. 15722
    Prev
    Next
    INDEX
    Explanations

    specialized program

    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
     entró
    -1.05
    cji
    -1.00
     anunció
    -0.99
     quas
    -0.96
     unabhäng
    -0.96
     kõik
    -0.94
    ńcu
    -0.93
    knapp
    -0.93
     publicó
    -0.93
    icordia
    -0.91
    POSITIVE LOGITS
    –
    1.02
     Russland
    0.91
    ஓ
    0.90
     piedras
    0.88
     minOccurs
    0.88
     actif
    0.87
     jdbcTemplate
    0.87
    0.87
    век
    0.86
    coronavirus
    0.85
    Activations Density 0.086%

    No Known Activations