© 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. 34875
    Prev
    Next
    INDEX
    Explanations

    common, Facebook, hours, transactions

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

    shapes, states, and connections

    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
     heen
    0.52
     extends
    0.51
    y
    0.49
     Refs
    0.47
     Ref
    0.47
     To
    0.46
    ona
    0.46
     =
    0.45
     .
    0.44
     Examples
    0.44
    POSITIVE LOGITS
    भारत
    0.50
    డ్‌
    0.49
    셸
    0.49
    驩
    0.48
    ड़िया
    0.47
    ждению
    0.47
    ジャン
    0.46
    скус
    0.46
    斯坦
    0.46
    ovým
    0.46
    Activations Density 0.000%

    No Known Activations