© 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. 210586
    Prev
    Next
    INDEX
    Explanations

    Wrigley Field

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

    investment in core areas

    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
    поло
    0.47
     sammen
    0.45
     plais
    0.45
    ık
    0.44
    ındaki
    0.42
    ₅
    0.42
    корд
    0.42
     kami
    0.41
    agiarism
    0.41
     begeistert
    0.41
    POSITIVE LOGITS
    Callable
    0.49
    स
    0.46
    CONS
    0.45
     TREAT
    0.45
    勅
    0.44
     Communism
    0.43
     delito
    0.42
    ສາ
    0.42
    ず
    0.42
     treaties
    0.41
    Activations Density 0.001%

    No Known Activations