© 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. 85374
    Prev
    Next
    INDEX
    Explanations

    internet explorer site

    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
    2
    -2.53
    1
    -2.44
    4
    -2.28
    6
    -2.23
    7
    -2.13
    9
    -2.05
    8
    -1.91
    5
    -1.88
     for
    -1.88
    3
    -1.86
    POSITIVE LOGITS
    裢
    1.99
     včetně
    1.89
     semelh
    1.87
    
    1.84
    decided
    1.84
     concerne
    1.81
    鼍
    1.80
    attended
    1.78
    ⠀⠀
    1.77
     saud
    1.77
    Activations Density 0.317%

    No Known Activations