© 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. 35143
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets

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

    bracketed information to replace

    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
    ۱
    0.47
     ی
    0.45
     லா
    0.43
     ک
    0.43
     prikaz
    0.42
     اطراف
    0.42
     Typography
    0.41
     withd
    0.40
     dentro
    0.38
    یس
    0.38
    POSITIVE LOGITS
    Ethoxy
    0.45
     joint
    0.44
     совме
    0.43
    Joint
    0.41
    第
    0.39
     Hoos
    0.39
     зави
    0.39
    UO
    0.38
     sophistic
    0.38
    াত
    0.38
    Activations Density 0.000%

    No Known Activations