© 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. 70149
    Prev
    Next
    INDEX
    Explanations

    also as

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

    epsilon and math symbols

    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
    Ș
    0.46
    Q
    0.44
     artery
    0.44
    ಲ್
    0.44
    त
    0.43
    arra
    0.42
    ৃ
    0.41
    ে
    0.41
    なし
    0.41
    䢂
    0.41
    POSITIVE LOGITS
     amaç
    0.44
     Henson
    0.43
     النص
    0.42
     Zul
    0.41
     trồng
    0.40
     grit
    0.38
     шер
    0.38
     zorgt
    0.38
     целью
    0.38
     Schwerpunkt
    0.38
    Activations Density 0.000%

    No Known Activations