© 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. 201460
    Prev
    Next
    INDEX
    Explanations

    Models in code namespaces

    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
    㡱
    0.40
    ทร
    0.39
     erhe
    0.39
     গর
    0.38
    शाला
    0.38
    ਣ
    0.38
    桅
    0.37
    رل
    0.37
    zeug
    0.36
     kilometre
    0.36
    POSITIVE LOGITS
    raw
    0.49
     intuitively
    0.45
    bind
    0.45
    الن
    0.44
     alguno
    0.44
    startsWith
    0.41
    ائی
    0.41
    cate
    0.41
     SO
    0.40
    RAW
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.