© 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. 133183
    Prev
    Next
    INDEX
    Explanations

    booklet, container, iris, latest

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

    purpose, suggestion, safely

    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
    c
    0.52
     closeness
    0.49
    h
    0.48
    p
    0.47
    二人
    0.46
    आती
    0.43
    兩人
    0.42
    杨
    0.42
    清新
    0.41
    i
    0.41
    POSITIVE LOGITS
    WallArray
    0.55
    playable
    0.48
     Реа
    0.48
    ⇐
    0.48
     سي
    0.47
     ingles
    0.47
     시행
    0.46
     Aussage
    0.45
     ом
    0.45
     سير
    0.44
    Activations Density 0.001%

    No Known Activations