© 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. 32943
    Prev
    Next
    INDEX
    Explanations

    words ending in ty followed by semicolon

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

    python import random

    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
    カ
    0.40
    o
    0.40
    r
    0.38
    嘗試
    0.38
    ร
    0.38
    」
    0.38
    ιο
    0.37
    雛
    0.37
     pair
    0.37
     “
    0.36
    POSITIVE LOGITS
     espalda
    0.47
    jenih
    0.46
    प्लीट
    0.44
     matou
    0.44
    athyroid
    0.44
    ushu
    0.44
    ahay
    0.43
     chromospheric
    0.42
    ayeva
    0.42
    zczeg
    0.42
    Activations Density 0.000%

    No Known Activations