© 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. 229028
    Prev
    Next
    INDEX
    Explanations

    archaeological evidence

    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
    errorHandler
    0.45
    ฯ
    0.43
    ですよ
    0.42
    RequestHandler
    0.41
    FileUtils
    0.40
     Vulner
    0.40
    UPLOAD
    0.39
    Portada
    0.39
    ῎
    0.39
     ГӀ
    0.39
    POSITIVE LOGITS
     from
    0.50
     constituent
    0.49
     particles
    0.49
     combining
    0.48
     tiles
    0.48
     tokens
    0.48
     commuting
    0.47
     från
    0.46
     indices
    0.46
     प्लेटफॉर्म
    0.46
    Activations Density 0.000%

    No Known Activations