© 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. 13774
    Prev
    Next
    INDEX
    Explanations

    questions and exclamations

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

    questions about purpose or reason

    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
    我很
    0.43
     كويس
    0.42
    สัง
    0.41
     Propaganda
    0.40
     اتفاق
    0.39
    我觉得
    0.39
    ব্লিউ
    0.39
    磪
    0.38
     implications
    0.38
    italizationType
    0.38
    POSITIVE LOGITS
     भला
    0.63
    ?!
    0.51
    わざ
    0.49
    ంతరం
    0.47
    ?!?!
    0.47
     ?!
    0.46
    豈
    0.45
    何の
    0.43
    岂
    0.42
    !?
    0.41
    Activations Density 0.202%

    No Known Activations