© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 79611
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FieldName
    0.42
    Tampa
    0.42
    ungy
    0.42
    룽
    0.42
    Frozen
    0.40
    Breast
    0.40
    Macrophages
    0.39
    Turkey
    0.38
    বলের
    0.38
    Wikipedia
    0.37
    POSITIVE LOGITS
     lithium
    0.88
     bipolar
    0.82
     Lithium
    0.79
    锂
    0.66
     electrolyte
    0.63
    鋰
    0.63
    ipolar
    0.56
     electrolytes
    0.52
     batteries
    0.44
     dipolar
    0.44
    Activations Density 0.030%

    No Known Activations