© 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. 55702
    Prev
    Next
    INDEX
    Explanations

    Titles of respect

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

    titles and honorifics

    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
     ειδ
    0.49
    ۲
    0.49
    ២
    0.49
     অস্ট্রেল
    0.48
    িয়া
    0.48
    当た
    0.47
    ɪ
    0.47
    desc
    0.47
    ২০
    0.47
    [];
    0.46
    POSITIVE LOGITS
    께서
    0.84
    께
    0.65
     جناب
    0.51
     말씀
    0.50
     ท่าน
    0.49
     naše
    0.48
    idän
    0.48
    댁
    0.46
     nostre
    0.46
    ുടെ
    0.46
    Activations Density 0.035%

    No Known Activations