© 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. 60629
    Prev
    Next
    INDEX
    Explanations

    specific nouns in processes

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

    Q, SGD, SE, Descent

    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
    ﻟ
    0.44
    ดัง
    0.43
    ;
    0.41
     SEC
    0.41
    영
    0.41
    ഢ
    0.41
    Air
    0.40
     Poster
    0.40
     webpage
    0.40
     Clearing
    0.40
    POSITIVE LOGITS
     subtilis
    0.48
    agamanam
    0.47
    vět
    0.44
     Spanien
    0.44
     हिस्
    0.43
     détect
    0.43
    quiet
    0.43
    ref
    0.43
    chave
    0.42
    )}(
    0.42
    Activations Density 0.000%

    No Known Activations