© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27578
    Prev
    Next
    INDEX
    Explanations

    task completion or resolution

    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
     in
    -1.28
     are
    -0.96
    robot
    -0.94
     aparece
    -0.94
     You
    -0.94
    作り
    -0.93
    を防
    -0.91
     sucedió
    -0.90
     tengamos
    -0.89
     "
    -0.89
    POSITIVE LOGITS
     and
    1.31
    賂
    1.11
    Nilai
    1.07
    🩲
    1.07
    moil
    1.07
     tazas
    1.05
     Valuable
    1.00
    excellents
    0.98
     بودند
    0.98
     lèvres
    0.98
    Activations Density 0.000%

    No Known Activations