© 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. 231437
    Prev
    Next
    INDEX
    Explanations

    control and specific types

    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
     usuarios
    0.55
    éz
    0.54
    insuff
    0.52
    žem
    0.50
     менее
    0.49
     vaš
    0.49
     пользователей
    0.49
    稆
    0.49
    ség
    0.48
    íce
    0.48
    POSITIVE LOGITS
     Georgetown
    0.47
    خود
    0.46
    。
    0.45
    GT
    0.43
    Go
    0.42
    Business
    0.42
    GD
    0.42
    Giovanni
    0.42
    ۔
    0.42
    ัส
    0.42
    Activations Density 0.000%

    No Known Activations