© 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. 224076
    Prev
    Next
    INDEX
    Explanations

    financials, personal, crocodiles, business, conversion

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

    pursue what excites

    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
    da
    0.48
    .
    0.48
    在
    0.47
    وظ
    0.47
    oda
    0.46
    رات
    0.46
    理論
    0.46
    <0x80>
    0.45
     dhe
    0.44
    wür
    0.44
    POSITIVE LOGITS
     argentina
    0.54
     pursuance
    0.53
     अर्जेंटीना
    0.50
     ዓይነ
    0.50
     פ
    0.49
     attaining
    0.49
    Argentina
    0.49
     reside
    0.49
     Argentina
    0.48
     स
    0.48
    Activations Density 0.000%

    No Known Activations