© 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. 192206
    Prev
    Next
    INDEX
    Explanations

    Cancellation tab

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

    for fans asking

    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
    タル
    0.52
     enunciado
    0.49
     семь
    0.47
     прибыль
    0.47
    调整
    0.47
    ンスター
    0.47
    嘞
    0.47
    饭
    0.47
     именем
    0.46
    辣
    0.46
    POSITIVE LOGITS
    Vocabulary
    0.43
     vortices
    0.43
     wafer
    0.43
     vorticity
    0.43
     terrestrial
    0.42
     vanishing
    0.42
     Verkehrs
    0.42
     respiration
    0.41
     Kiến
    0.41
    MediaPath
    0.41
    Activations Density 0.000%

    No Known Activations