© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127458
    Prev
    Next
    INDEX
    Explanations

    compassion, soluble, pipe, mastitis

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

    The neuron activates for the word "compassion" and related terms about caring or empathy.

    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
    y
    -3.05
     continual
    -2.30
    CONSIN
    -2.28
    N
    -2.27
    ”—
    -2.23
     was
    -2.20
    囿
    -2.14
    s
    -2.06
    z
    -2.06
    ve
    -2.05
    POSITIVE LOGITS
    the
    2.66
     breite
    2.39
    鲩
    2.09
    selben
    2.08
    ..........
    2.06
    ↵
    2.05
    Ꮚ
    2.00
    𐀀
    1.98
     .......
    1.98
     vollständige
    1.94
    Activations Density 0.000%

    No Known Activations