© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10492
    Prev
    Next
    INDEX
    Explanations

    medical symptom descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    𒂗
    1.83
     सनातन
    1.79
    नई
    1.77
    >∞</
    1.75
     संजीव
    1.71
    酎
    1.69
    ፈላጊ
    1.67
     Wochschr
    1.65
    REQUIRE
    1.62
    upaten
    1.62
    POSITIVE LOGITS
    t
    1.59
    /
    1.32
    ിൽ
    1.30
    ing
    1.30
     vorm
    1.28
    ي
    1.27
    s
    1.25
    ie
    1.24
    ের
    1.24
    \
    1.22
    Activations Density 0.000%

    No Known Activations