© 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. 16342
    Prev
    Next
    INDEX
    Explanations

    end of clause or phrase

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

    not advice disclaimers

    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
    栤
    0.67
    <unused2123>
    0.65
    㛲
    0.63
    媢
    0.62
    <unused2152>
    0.61
    㺫
    0.60
    媑
    0.60
    Toplam
    0.59
    𒀕
    0.58
     автоматлары
    0.57
    POSITIVE LOGITS
    0.68
    5
    0.65
     h
    0.62
     a
    0.61
    3
    0.61
     l
    0.60
     d
    0.60
     (
    0.60
    s
    0.59
     S
    0.59
    Activations Density 0.078%

    No Known Activations