© 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. 10-GEMMASCOPE-RES-131K
    7. 99228
    Prev
    Next
    INDEX
    Explanations

    start of statements

    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_10/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
     "
    -3.14
    ৄ
    -2.66
    鉝
    -2.55
    </em>
    -2.52
    ."
    -2.42
    ︓
    -2.25
     et
    -2.17
     árvores
    -2.16
     But
    -2.14
    
    -2.14
    POSITIVE LOGITS
    to
    2.73
    </h1>
    2.41
    ";
    2.36
    豋
    2.17
    
    2.17
    都不会
    2.14
    宬
    2.13
     disminuir
    2.02
     costos
    2.00
    幛
    2.00
    Activations Density 0.006%

    No Known Activations