© 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. 224038
    Prev
    Next
    INDEX
    Explanations

    no mowing / in-display fingerprint

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

    explaining written or visual content

    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
     anillo
    0.54
     fech
    0.50
    参照
    0.49
     عندنا
    0.49
    骅
    0.48
     باسک
    0.46
    领取
    0.46
     verz
    0.46
     माझ्या
    0.46
    ிலிருந்த
    0.45
    POSITIVE LOGITS
    s
    0.57
    কথ
    0.49
    ों
    0.49
    ny
    0.43
    ating
    0.43
     indifference
    0.43
    ς
    0.43
    ktops
    0.42
    AVG
    0.42
    Yap
    0.41
    Activations Density 0.000%

    No Known Activations