© 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. 111566
    Prev
    Next
    INDEX
    Explanations

    amyloid precursor, stony, Lesotho

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

    The neuron detects terms related to amyloid proteins and compounds, particularly in scientific or medical contexts.

    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
    ing
    -2.61
    c
    -2.48
    F
    -2.45
    觧
    -2.34
    h
    -2.34
    繻
    -2.33
    ).
    -2.31
    雰
    -2.30
    います
    -2.27
    婬
    -2.27
    POSITIVE LOGITS
     You
    2.80
    béco
    2.41
    お勧め
    2.38
    ᗯ
    2.33
    ſſen
    2.28
     toutefois
    2.25
     然
    2.25
    ascin
    2.23
     男人
    2.20
    èges
    2.16
    Activations Density 0.015%

    No Known Activations