© 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. 100379
    Prev
    Next
    INDEX
    Explanations

    following phrases

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

    commands, systems, unique, Tuesday, conversations, trying, expect

    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
    不住
    0.50
    他们在
    0.48
    ாகு
    0.45
     computations
    0.44
    LE
    0.44
    ле
    0.44
    Maximize
    0.43
    テ
    0.43
     mereka
    0.42
    یه
    0.42
    POSITIVE LOGITS
     పలు
    0.57
     Floral
    0.54
     Vent
    0.54
     광
    0.53
     హైదర్
    0.53
     vent
    0.49
     ['
    0.49
     $[
    0.49
     [+
    0.49
     Lens
    0.48
    Activations Density 0.001%

    No Known Activations