© 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. 34466
    Prev
    Next
    INDEX
    Explanations

    bifurcation, parameter, twists, changes

    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
    kka
    -0.94
    RAE
    -0.91
    盗
    -0.89
     быстрее
    -0.88
    algorithms
    -0.87
     patio
    -0.86
    ITAS
    -0.83
     парфю
    -0.82
    luor
    -0.82
    umia
    -0.82
    POSITIVE LOGITS
    尔夫
    1.00
     alterations
    0.96
    changes
    0.96
     changes
    0.94
     kurikulum
    0.93
     divertida
    0.91
     pries
    0.90
     Blum
    0.90
    sanity
    0.90
    녔
    0.89
    Activations Density 0.030%

    No Known Activations