© 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. 218964
    Prev
    Next
    INDEX
    Explanations

    multilingual communication

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

    citrus, wind, cooling, permission

    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
    ἔ
    0.52
    ငံ
    0.51
    ies
    0.51
    )."
    0.49
     involves
    0.49
     WEIGHT
    0.49
    <unused2069>
    0.48
     Plastics
    0.48
    ATIVES
    0.48
    🙂
    0.48
    POSITIVE LOGITS
     थी
    0.50
    0.50
     был
    0.43
    一阵
    0.43
     hadde
    0.42
     newspaper
    0.42
    眼前
    0.42
     був
    0.39
     byl
    0.39
     Ottoman
    0.39
    Activations Density 0.004%

    No Known Activations