© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73155
    Prev
    Next
    INDEX
    Explanations

    code declarations and identifiers

    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
    according
    -1.23
    those
    -1.13
     Tiếng
    -1.08
     Welche
    -1.08
     Entsche
    -1.00
     obcí
    -1.00
    gridColumn
    -0.99
     superiore
    -0.99
     específica
    -0.99
     Häufig
    -0.98
    POSITIVE LOGITS
     an
    1.43
     a
    1.40
     another
    1.32
    createNewFile
    0.98
     ambiental
    0.94
     estancias
    0.91
     суть
    0.90
    ()]
    
    0.90
    epsilon
    0.89
     agricultura
    0.89
    Activations Density 0.005%

    No Known Activations