© 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. 30671
    Prev
    Next
    INDEX
    Explanations

    tooth and dental care

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

    certain medications

    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
     প্রবণ
    0.40
     নিজের
    0.40
     Lesen
    0.40
     ف
    0.40
     Bücher
    0.38
    ারের
    0.38
     Kosten
    0.37
     ric
    0.37
     ماذا
    0.37
    蛜
    0.37
    POSITIVE LOGITS
    ণ্
    0.42
     iod
    0.38
    aré
    0.36
     crossbody
    0.36
    oł
    0.36
    చే
    0.36
     assent
    0.36
     dietitian
    0.35
    Adi
    0.35
     oxford
    0.35
    Activations Density 0.000%

    No Known Activations