© 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. 57548
    Prev
    Next
    INDEX
    Explanations

    general specific examples

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

    food legality

    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
    腑
    0.45
    inesh
    0.41
    inales
    0.41
    िटी
    0.40
    以外の
    0.40
    ionalmente
    0.40
    ewo
    0.40
    Artículo
    0.40
    ễ
    0.40
    ButtonBar
    0.40
    POSITIVE LOGITS
    aing
    0.51
    band
    0.47
     assemblage
    0.46
     ung
    0.44
     ؛
    0.44
    waterslide
    0.44
    badges
    0.43
     कक्ष
    0.42
     carts
    0.41
     sterk
    0.41
    Activations Density 0.001%

    No Known Activations