© 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. 15813
    Prev
    Next
    INDEX
    Explanations

    advertising on gundogs.com

    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
     again
    -1.10
    仍然
    -0.96
    依然
    -0.96
    Again
    -0.94
    摂取
    -0.94
     nying
    -0.92
    ིག་
    -0.91
    에서
    -0.90
     Gastgeber
    -0.89
     baada
    -0.89
    POSITIVE LOGITS
    ledning
    1.00
    филь
    1.00
    氏が
    0.98
    
    0.98
    ṝ
    0.95
     which
    0.95
     аль
    0.93
     नंबर
    0.93
     what
    0.91
    优雅
    0.91
    Activations Density 0.003%

    No Known Activations