© 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. 37293
    Prev
    Next
    INDEX
    Explanations

    sequences followed by specific words

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

    generate helpful content

    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
    e
    0.51
     the
    0.50
    ựng
    0.47
    ev
    0.46
     Bronze
    0.46
    the
    0.46
     Rainbow
    0.46
    omed
    0.45
    y
    0.45
     Yon
    0.45
    POSITIVE LOGITS
    缚
    0.52
    нтип
    0.51
    כים
    0.49
     appease
    0.49
     внимания
    0.48
     confuses
    0.47
     ঊর্ধ্বতন
    0.46
    氛
    0.46
    нета
    0.46
     psychos
    0.45
    Activations Density 0.000%

    No Known Activations