© 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. 33082
    Prev
    Next
    INDEX
    Explanations

    dates, questions, quotes, code

    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
    २
    -1.13
     that
    -1.09
     since
    -1.07
     who
    -1.05
     your
    -1.02
     every
    -0.98
     unidos
    -0.98
    GRAFÍA
    -0.98
     eleições
    -0.97
    ३
    -0.96
    POSITIVE LOGITS
    دانلود
    1.15
    Recept
    1.13
    Legenda
    1.13
    Karel
    1.05
    ktion
    1.04
    FOTO
    1.04
    rece
    1.03
    Impression
    1.01
    Rusia
    1.01
     heath
    1.00
    Activations Density 0.002%

    No Known Activations