© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8624
    Prev
    Next
    INDEX
    Explanations

    baseball and cricket batters

    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
    ’
    -2.78
    }$
    -2.20
    其他的
    -2.14
     catedral
    -2.11
    These
    -2.03
    Some
    -2.03
     of
    -2.03
    Other
    -2.00
    It
    -1.92
    　　-
    -1.92
    POSITIVE LOGITS
    皷
    2.70
    檮
    2.47
     tématu
    2.05
     skoro
    2.03
    拶
    2.03
     zapal
    2.00
    dersfield
    1.99
     gemeenten
    1.97
     apresentam
    1.97
    犼
    1.94
    Activations Density 0.004%

    No Known Activations