© 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. 155050
    Prev
    Next
    INDEX
    Explanations

    conditional introductions

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

    practical, future, important, what

    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
    푞
    0.49
    矢
    0.48
    ﮯ
    0.48
    ミ
    0.47
    및
    0.46
    Departamento
    0.46
    ※
    0.46
    箭
    0.46
    Número
    0.45
     與
    0.45
    POSITIVE LOGITS
    it
    0.56
    lt
    0.51
     PHP
    0.49
    entr
    0.46
     perilaku
    0.46
     It
    0.44
     LOS
    0.43
    ize
    0.43
     joueur
    0.43
     Los
    0.41
    Activations Density 0.002%

    No Known Activations