© 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. 19399
    Prev
    Next
    INDEX
    Explanations

    calling 911

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

    figuring out what

    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
    ד
    0.57
    фа
    0.51
    רי
    0.49
    מ
    0.48
    мі
    0.48
    ட
    0.47
    タ
    0.47
    ジ
    0.47
    親
    0.47
    то
    0.47
    POSITIVE LOGITS
    uland
    0.51
    நிலை
    0.45
     căn
    0.45
     पुल्लिंग
    0.44
     शीतल
    0.44
    ݨ
    0.44
    Ning
    0.43
    Tmp
    0.42
     거고
    0.42
     TextInputLayout
    0.42
    Activations Density 0.000%

    No Known Activations