© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13985
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    validating, control, asking, holiday

    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
    <b>
    0.42
    يت
    0.41
     ngo
    0.40
    。
    0.38
    Entropy
    0.38
    e
    0.38
    ”
    0.37
    들과
    0.37
    -
    0.37
     hivyo
    0.36
    POSITIVE LOGITS
     война
    0.45
     হ্
    0.45
    চিতের
    0.44
     पो
    0.44
     achten
    0.44
     porté
    0.44
    ポン
    0.43
     женой
    0.43
     設定
    0.43
    porte
    0.42
    Activations Density 1.219%

    No Known Activations