© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72642
    Prev
    Next
    INDEX
    Explanations

    Russian Turkish operation

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

    gangsters to their younger brothers

    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
    Ꭷ
    0.44
     posled
    0.44
     banknote
    0.44
     série
    0.44
    Ꮿ
    0.43
    Product
    0.43
    Ꮭ
    0.42
     rangkaian
    0.42
    ጋገብ
    0.42
     matière
    0.42
    POSITIVE LOGITS
     APIs
    0.51
    ”;
    0.49
     Paxton
    0.48
     IPA
    0.48
     ASM
    0.46
     EGFR
    0.46
    jn
    0.45
     Andrews
    0.45
     ASI
    0.44
     நடி
    0.44
    Activations Density 0.001%

    No Known Activations