© 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. 100045
    Prev
    Next
    INDEX
    Explanations

    golfing, golfer, golf balls

    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
    ”
    -3.02
    ]
    -2.88
    $
    -2.58
    x
    -2.52
    ścioła
    -2.44
    that
    -2.22
    ),
    -2.13
    梘
    -2.08
    =
    -2.08
    儈
    -2.00
    POSITIVE LOGITS
     of
    2.63
    蜮
    2.39
    I
    2.20
    風呂
    2.14
     Their
    2.06
    
    2.02
    玬
    1.98
     indivíduos
    1.95
     În
    1.91
     preferências
    1.90
    Activations Density 0.004%

    No Known Activations