© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15930
    Prev
    Next
    INDEX
    Explanations

    reference design or image

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

    paranoia books

    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
     концер
    0.50
    罵
    0.47
    薦
    0.46
    哂
    0.46
     хирур
    0.46
     ঘরে
    0.45
    栻
    0.45
     аллер
    0.45
    Consulta
    0.45
    Speakers
    0.45
    POSITIVE LOGITS
    ្សា
    0.55
     others
    0.52
    others
    0.52
     des
    0.51
    ",
    0.50
     actor
    0.50
     h
    0.49
    str
    0.49
     voy
    0.48
    pros
    0.48
    Activations Density 0.000%

    No Known Activations