© 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. 13378
    Prev
    Next
    INDEX
    Explanations

    multilingual contexts

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

    R, C, and apple references

    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
    atious
    0.44
     colorless
    0.44
     propulsion
    0.44
     watercolors
    0.43
    bred
    0.42
     siker
    0.42
    plic
    0.42
     a
    0.41
     reigning
    0.41
     jer
    0.40
    POSITIVE LOGITS
    ى
    0.58
     まとめ
    0.51
    کی
    0.50
    ่
    0.49
     作り
    0.49
    츨
    0.46
     utilisé
    0.46
     consideramos
    0.46
    টির
    0.46
    ো
    0.46
    Activations Density 0.000%

    No Known Activations