© 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. 45811
    Prev
    Next
    INDEX
    Explanations

    national team selection

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

    national team selection

    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
     మొక్క
    0.46
    食べ
    0.45
    燜
    0.44
     rigged
    0.43
    店舗
    0.43
     empleado
    0.42
    鈷
    0.42
    Unhandled
    0.42
    鹸
    0.42
    ἦ
    0.42
    POSITIVE LOGITS
     selectors
    0.75
    selection
    0.74
     selection
    0.68
     المنتخب
    0.66
     Selection
    0.63
    Selection
    0.61
     seleção
    0.60
     selección
    0.59
     selezione
    0.58
     चयन
    0.57
    Activations Density 0.060%

    No Known Activations