© 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. 36800
    Prev
    Next
    INDEX
    Explanations

    two outs

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

    statement continuation

    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
    О
    0.47
    Т
    0.46
    Бы
    0.46
    उनकी
    0.44
    目で
    0.43
     दौड़
    0.43
     politici
    0.42
    Deutsch
    0.41
    Б
    0.41
     каждого
    0.41
    POSITIVE LOGITS
     فلا
    0.44
     thereby
    0.43
     να
    0.41
     stresses
    0.40
     shaft
    0.40
     impetus
    0.40
     folly
    0.40
     submerged
    0.38
     rather
    0.38
     radius
    0.38
    Activations Density 0.001%

    No Known Activations