© 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. 40-GEMMASCOPE-2-RES-16K
    7. 11282
    Prev
    Next
    INDEX
    Explanations

    "And" and biblical quotes

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

    biblical or archaic prose

    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_40_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
     boldness
    0.46
    픕
    0.44
     તમારે
    0.43
    谜
    0.43
    真正的
    0.42
    ǎn
    0.42
     atthakath
    0.41
    Validator
    0.40
     quickest
    0.40
     നിങ്ങൾ
    0.40
    POSITIVE LOGITS
    lime
    0.43
    phonic
    0.42
    butan
    0.42
    <unused61>
    0.40
    ym
    0.39
    fte
    0.39
    civ
    0.38
     Nay
    0.38
    de
    0.38
     Har
    0.38
    Activations Density 0.078%

    No Known Activations