© 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. 219612
    Prev
    Next
    INDEX
    Explanations

    strategic sourcing

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

    punctuation and common words

    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
    絫
    0.48
    GORITHM
    0.46
    ibilities
    0.45
    GULD
    0.44
     मांस
    0.44
    ivals
    0.44
     สิ
    0.44
    ñones
    0.44
     საკ
    0.43
    åd
    0.43
    POSITIVE LOGITS
    l
    0.50
    t
    0.48
    minded
    0.46
    v
    0.46
     oran
    0.45
     alumno
    0.44
     cheerfully
    0.44
     स्टूडेंट
    0.42
     Übersetzung
    0.42
    تف
    0.42
    Activations Density 0.001%

    No Known Activations