© 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. 220535
    Prev
    Next
    INDEX
    Explanations

    分享, 篇, 於, 有, 其它

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

    From tiny seeds

    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
    klassen
    0.60
    ఙ
    0.59
     arrondi
    0.50
     manglid
    0.50
     দিয়াছেন
    0.49
     আয়নের
    0.49
    娀
    0.49
     コットン
    0.49
    質
    0.49
    mirea
    0.48
    POSITIVE LOGITS
    0.50
     Natural
    0.44
     Celebr
    0.43
    p
    0.42
    ...",
    0.41
     Gul
    0.41
     Bread
    0.40
     looting
    0.40
     Biochemistry
    0.40
     Warfare
    0.40
    Activations Density 0.000%

    No Known Activations