© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21546
    Prev
    Next
    INDEX
    Explanations

    superstar athletes

    np_acts-logits-general · gemini-2.5-flash-lite

    Lionel Messi's greatness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    灰
    0.56
    Tarea
    0.52
    Noir
    0.47
    婦
    0.47
    ৤
    0.47
    ঙ্খ
    0.47
    觀塘
    0.47
    brown
    0.46
     Thứ
    0.46
    亻
    0.46
    POSITIVE LOGITS
     superstar
    1.02
     superstars
    0.96
     सुपरस्टार
    0.95
     majest
    0.88
     dominating
    0.84
     unrival
    0.83
     superhuman
    0.80
     LeBron
    0.79
     Superstar
    0.79
     superman
    0.78
    Activations Density 0.174%

    No Known Activations