© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16316
    Prev
    Next
    INDEX
    Explanations

    features, offers, actions

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

    continuations after punctuation

    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_16k_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
    the
    0.47
     বেশ
    0.47
    elsen
    0.46
     ব্যাপক
    0.45
     khá
    0.45
    apol
    0.45
    sen
    0.45
    à
    0.44
     जबरदस्त
    0.44
     and
    0.44
    POSITIVE LOGITS
    给你
    0.50
     legyen
    0.48
     umož
    0.47
    允許
    0.47
    让你
    0.46
    允许
    0.46
     alcançar
    0.45
     purest
    0.45
    彰
    0.44
     Cannot
    0.44
    Activations Density 0.071%

    No Known Activations