© 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. 38888
    Prev
    Next
    INDEX
    Explanations

    to let know

    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
    section
    -2.38
    鋮
    -2.00
     épocas
    -1.88
     якщо
    -1.85
     pervasive
    -1.84
    lgari
    -1.83
    And
    -1.82
     возгла
    -1.81
     diligent
    -1.80
    ſelves
    -1.76
    POSITIVE LOGITS
    歺
    2.66
    犼
    2.39
    桫
    2.33
    扨
    2.13
    
    2.09
    ໊
    2.06
    沵
    2.02
    跸
    2.02
    
    1.97
    栳
    1.97
    Activations Density 0.003%

    No Known Activations