© 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. 21810
    Prev
    Next
    INDEX
    Explanations

    lights under

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

    foreign language or linguistic constructs

    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
    쨋
    0.47
    Ａ
    0.46
    Ľ
    0.45
     जनता
    0.44
    기고
    0.43
    Ｇ
    0.43
    Gov
    0.43
    ancies
    0.42
    렸
    0.41
    пута
    0.41
    POSITIVE LOGITS
     என்கிறார்
    0.50
     نہیں۔
    0.47
     externe
    0.47
     external
    0.45
     choral
    0.44
     multifunctional
    0.43
     लौटने
    0.42
     외부
    0.42
     syntactic
    0.42
     sœur
    0.41
    Activations Density 0.000%

    No Known Activations