© 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. 164598
    Prev
    Next
    INDEX
    Explanations

    common collocations

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

    qualities and outcomes

    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
     homotopy
    0.47
    ophyllum
    0.47
    佾
    0.46
    并发
    0.46
     irreducible
    0.45
    HINSTANCE
    0.44
     ব্যাটিং
    0.44
    期刊
    0.44
    镜
    0.44
    鼐
    0.43
    POSITIVE LOGITS
     ede
    0.49
    ᴍ
    0.47
     runs
    0.45
    وک
    0.45
     auss
    0.44
     on
    0.44
    HOUT
    0.44
     nedeniyle
    0.44
    erde
    0.43
     دوس
    0.42
    Activations Density 0.000%

    No Known Activations