© 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. 160844
    Prev
    Next
    INDEX
    Explanations

    . / ִי

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

    operates or relates to technology

    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
    zyme
    0.50
    噌
    0.46
    ските
    0.46
     populaire
    0.44
    琐
    0.44
     HAM
    0.44
    字
    0.44
     cellulaire
    0.43
    zaam
    0.43
    ップ
    0.43
    POSITIVE LOGITS
     万
    0.54
     jamás
    0.54
     perpetually
    0.49
     そんな
    0.47
    designs
    0.46
     लाखों
    0.46
     می‌کنند
    0.45
     millones
    0.44
     beginnings
    0.44
    Gonz
    0.44
    Activations Density 0.000%

    No Known Activations