© 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. 79611
    Prev
    Next
    INDEX
    Explanations

    lithium, bipolar disorder, batteries

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

    lithium batteries and bipolar disorder

    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
    룽
    0.46
    ungy
    0.45
    छोटे
    0.42
    Breast
    0.42
    συ
    0.41
    রের
    0.41
     नग
    0.41
    Tampa
    0.41
    舧
    0.40
    til
    0.40
    POSITIVE LOGITS
     lithium
    0.96
     Lithium
    0.91
     bipolar
    0.82
    锂
    0.73
     electrolyte
    0.64
    鋰
    0.64
     batteries
    0.59
     electrolytes
    0.56
    ipolar
    0.54
     battery
    0.54
    Activations Density 0.020%

    No Known Activations