© 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. 66870
    Prev
    Next
    INDEX
    Explanations

    epoxy, Jody, EMI, EGR, Gino, Eddy, XII

    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
    ⢪
    -3.59
    噥
    -2.95
    鏷
    -2.84
    鶘
    -2.81
    StoryboardSegue
    -2.77
    筺
    -2.75
    linawan
    -2.64
     หรือ
    -2.61
    
    -2.59
     encontrados
    -2.56
    POSITIVE LOGITS
    {
    3.77
    ):
    3.02
    (
    2.81
    *
    2.70
     '
    2.70
    \"
    2.66
    A
    2.47
                    
    2.38
    This
    2.36
    了很多
    2.27
    Activations Density 0.018%

    No Known Activations