© 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. 161042
    Prev
    Next
    INDEX
    Explanations

    army irrigation specialist

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

    lost or forgotten items

    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
    یط
    0.57
    邁
    0.56
    部分は
    0.51
     mesurer
    0.50
    ಾರಿ
    0.49
    рами
    0.47
    выми
    0.47
    ﮢ
    0.46
    리아
    0.46
    אות
    0.46
    POSITIVE LOGITS
    i
    0.62
     Sno
    0.52
     bespoke
    0.52
     apartheid
    0.50
    to
    0.49
     Samuel
    0.48
     nhật
    0.48
    general
    0.48
     Casper
    0.48
     cyber
    0.47
    Activations Density 0.000%

    No Known Activations