© 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. 224981
    Prev
    Next
    INDEX
    Explanations

    multi-lingual content detection

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

    common operating procedures

    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
    U
    0.52
    T
    0.50
     mRNA
    0.48
     Lorentz
    0.47
     Yung
    0.47
    J
    0.47
    Lore
    0.46
    G
    0.46
    il
    0.45
     Lorenz
    0.45
    POSITIVE LOGITS
    といえば
    0.60
     якого
    0.53
     guerras
    0.53
    лі
    0.51
     trigo
    0.51
     اريد
    0.49
     obstáculos
    0.48
    ляются
    0.47
     chứ
    0.47
    地の
    0.47
    Activations Density 0.002%

    No Known Activations