© 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. 209763
    Prev
    Next
    INDEX
    Explanations

    class definitions and notes

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

    if followed by returns or none

    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
    我们要
    0.52
    述
    0.49
    ที่เรา
    0.45
    我們要
    0.42
    onać
    0.42
     отвеча
    0.42
     आल्या
    0.41
    键
    0.41
    我们需要
    0.40
    owy
    0.40
    POSITIVE LOGITS
    Flags
    0.45
     Cf
    0.44
     altres
    0.44
    ടൊപ്പം
    0.43
     $<\
    0.42
    Cf
    0.42
    Académie
    0.42
     École
    0.41
     tudi
    0.40
     Esso
    0.40
    Activations Density 0.043%

    No Known Activations