© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112002
    Prev
    Next
    INDEX
    Explanations

    neurobiology and toxicity

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

    terms related to neurobiology, neurological conditions, and brain science.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    لقاء
    -2.06
    Beskrivning
    -1.86
     tristes
    -1.85
    鲆
    -1.85
     spannend
    -1.84
    ᠊
    -1.84
     аккура
    -1.83
     ""],
    -1.82
    इटम
    -1.79
    
    -1.78
    POSITIVE LOGITS
     of
    2.16
     and
    1.72
    槃
    1.63
     brinda
    1.62
     consigue
    1.59
     distinguishes
    1.58
     estudia
    1.58
    梣
    1.55
     will
    1.54
    場合
    1.51
    Activations Density 0.066%

    No Known Activations