© 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. 76674
    Prev
    Next
    INDEX
    Explanations

    actions and outcomes

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

    foreign language texts

    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
    ཊ
    0.44
    ^{
    0.42
    님의
    0.41
    ান
    0.41
    𝗻
    0.40
     combination
    0.39
    excess
    0.39
    থ
    0.39
    エネルギー
    0.39
    combination
    0.39
    POSITIVE LOGITS
     Раз
    0.49
     Dlatego
    0.48
     Daarna
    0.47
     Ми
    0.47
     Giá
    0.46
     Zá
    0.46
     دلچ
    0.46
     ลง
    0.46
     ადა
    0.46
     perpetuate
    0.45
    Activations Density 0.001%

    No Known Activations