© 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. 142885
    Prev
    Next
    INDEX
    Explanations

    back again assistance

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

    **Term** followed by **Investment**

    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
    📡
    0.54
    áš
    0.53
    akh
    0.50
     おはよう
    0.48
    iking
    0.48
     လူ
    0.48
     活动
    0.47
     Docker
    0.45
     ახ
    0.45
     الجهاز
    0.45
    POSITIVE LOGITS
    c
    0.57
    the
    0.57
    продук
    0.56
    an
    0.55
    as
    0.52
    re
    0.52
    ра
    0.52
    la
    0.51
    стри
    0.51
    ре
    0.48
    Activations Density 0.000%

    No Known Activations