© 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. 209856
    Prev
    Next
    INDEX
    Explanations

    electronic component identifiers

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

    economic and social issues

    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
     vehemently
    0.52
     angrily
    0.51
     °,
    0.49
     usurp
    0.47
     appellee
    0.46
    立即
    0.46
     neurotrans
    0.46
     acuity
    0.46
     дочь
    0.46
     impatiently
    0.45
    POSITIVE LOGITS
    h
    0.46
    IO
    0.43
    ولة
    0.42
    लाइ
    0.42
    त
    0.41
    یا
    0.41
    坐标
    0.41
    io
    0.40
     pha
    0.40
    ersiz
    0.39
    Activations Density 0.001%

    No Known Activations