© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 163521
    Prev
    Next
    INDEX
    Explanations

    for that must

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

    strength of evidence or likelihood

    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
    ност
    0.49
    惴
    0.49
    演出
    0.48
    є
    0.48
    站在
    0.46
     мотива
    0.46
    тал
    0.46
    ทางการ
    0.46
     પોસ્ટ
    0.45
    σαν
    0.45
    POSITIVE LOGITS
     (
    0.55
     floc
    0.46
     Select
    0.45
     بجلی
    0.45
     demonstrated
    0.44
     poder
    0.44
     دما
    0.44
     power
    0.44
     O
    0.44
     ((
    0.44
    Activations Density 0.002%

    No Known Activations