© 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. 60128
    Prev
    Next
    INDEX
    Explanations

    Lionel Messi, Ritchie, Hampton

    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
    d
    -3.45
    ?
    -2.73
    w
    -2.59
     thinks
    -2.52
    p
    -2.42
    g
    -2.39
    what
    -2.36
    ers
    -2.33
     👀
    -2.28
    ↵↵
    -2.25
    POSITIVE LOGITS
    琑
    3.05
    嫑
    2.89
     concepción
    2.84
    旆
    2.84
    孥
    2.81
    籥
    2.80
     própri
    2.77
    蘩
    2.70
    .’
    2.64
    秾
    2.59
    Activations Density 0.009%

    No Known Activations