© 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. 180815
    Prev
    Next
    INDEX
    Explanations

    room when

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

    roles and lists

    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
    D
    0.62
    N
    0.51
    T
    0.50
    Z
    0.50
    G
    0.49
    E
    0.48
    H
    0.48
    Sciences
    0.47
     Princip
    0.47
    K
    0.46
    POSITIVE LOGITS
     hồn
    0.54
    ième
    0.53
    𝕖
    0.52
     بتساوي
    0.52
     '_
    0.49
     দলের
    0.48
     लड़ाई
    0.47
     ملازمت
    0.47
    ｆ
    0.47
     لڑ
    0.47
    Activations Density 0.001%

    No Known Activations