© 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. 166092
    Prev
    Next
    INDEX
    Explanations

    quotations and self-referential statements

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

    "I" followed by punctuation

    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
     acompan
    0.39
     inaugur
    0.39
    嚩
    0.38
    Beijing
    0.37
     Aaj
    0.37
     supernatant
    0.37
     offseason
    0.36
     SLASH
    0.36
    對
    0.36
     foils
    0.36
    POSITIVE LOGITS
    ෙහි
    0.44
     எல்லோ
    0.41
    我不
    0.41
     प्रश्‍
    0.40
     δεν
    0.40
    trust
    0.40
     ඒ
    0.40
    ಿದ್ದೇನೆ
    0.39
    leye
    0.39
    ucia
    0.38
    Activations Density 0.035%

    No Known Activations