© 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. 208651
    Prev
    Next
    INDEX
    Explanations

    do so, does

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

    predatory smile, fail internally, such themes, helps reduce

    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
    াসা
    0.42
    permutation
    0.41
    ">/</
    0.41
    eta
    0.40
    жы
    0.40
    uta
    0.39
    ሬ
    0.39
    住
    0.38
    ों
    0.38
     sd
    0.38
    POSITIVE LOGITS
     তারাও
    0.55
     ebenfalls
    0.51
     çiçek
    0.47
     তারাই
    0.46
    Danke
    0.43
    atthena
    0.42
     öffentlich
    0.42
    🕷
    0.42
    irme
    0.42
    اعری
    0.42
    Activations Density 0.000%

    No Known Activations