© 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. 158552
    Prev
    Next
    INDEX
    Explanations

    taking medication

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

    factors and values

    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
     König
    0.56
    㜖
    0.50
     Ländern
    0.50
     ఉంది
    0.49
    ن
    0.49
    函数的
    0.48
    㹮
    0.48
    س
    0.48
     erscheinen
    0.47
     Kollegen
    0.46
    POSITIVE LOGITS
    der
    0.60
    ade
    0.60
    ert
    0.58
    ate
    0.57
    ers
    0.56
    er
    0.55
    ing
    0.55
    ce
    0.55
    za
    0.54
    ech
    0.54
    Activations Density 0.001%

    No Known Activations