© 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. 70416
    Prev
    Next
    INDEX
    Explanations

    kilometers followed by period

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

    psychosis, paranoia, mental health

    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
    hin
    0.49
     बेबी
    0.46
    邀
    0.46
     मेगापिक्सल
    0.46
     ব্রহ্ম
    0.45
    again
    0.44
     ಭೂ
    0.43
     "-"]
    0.43
     berbagi
    0.43
    dert
    0.42
    POSITIVE LOGITS
    Indexed
    0.44
    κτήθηκε
    0.42
    に入
    0.42
     understands
    0.42
    :
    0.42
    جه
    0.40
    우스
    0.40
    ASP
    0.40
     alphabetical
    0.40
     Understand
    0.39
    Activations Density 0.001%

    No Known Activations