© 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. 33049
    Prev
    Next
    INDEX
    Explanations

    system command calls

    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
    ように
    -1.18
    
    -1.08
    只剩
    -1.08
    ≮
    -1.00
    operatively
    -0.99
    ्यालय
    -0.99
    ⊓
    -0.99
    IFORNIA
    -0.97
    為に
    -0.97
    weds
    -0.94
    POSITIVE LOGITS
    -
    1.06
    what
    0.97
    lysm
    0.95
     what
    0.95
    🪲
    0.95
     temporadas
    0.90
     erwerben
    0.90
     expectativas
    0.90
    回应
    0.90
     it
    0.90
    Activations Density 0.005%

    No Known Activations