© 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. 14216
    Prev
    Next
    INDEX
    Explanations

    proliferative, lifer, Kalman, Assam

    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
     extrême
    -2.52
     overarching
    -2.50
    崃
    -2.50
    壜
    -2.50
     Careful
    -2.48
     společ
    -2.39
     enquête
    -2.38
    B
    -2.38
     Notably
    -2.34
    .
    -2.34
    POSITIVE LOGITS
    寕
    3.47
    ৄ
    2.77
    y
    2.45
    .”
    2.34
    堙
    2.30
    
    2.30
    CHREIB
    2.28
     to
    2.28
     preferências
    2.25
     BRARY
    2.25
    Activations Density 0.039%

    No Known Activations