© 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. 66622
    Prev
    Next
    INDEX
    Explanations

    evidence of or that

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

    The neuron fires on the word “evidence,” i.e. it detects occurrences of “evidence” (often in “evidence of …” contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    一些
    -1.92
    ي
    -1.72
    笑笑
    -1.71
    บาง
    -1.63
    ⛷
    -1.61
    ⃙
    -1.59
    谕
    -1.54
     and
    -1.53
    fiets
    -1.52
    னர்
    -1.46
    POSITIVE LOGITS
     that
    2.08
    s
    1.91
    ↵↵
    1.76
    ar
    1.60
     zanahoria
    1.51
     argues
    1.48
     señora
    1.46
    “
    1.42
    终究
    1.41
    筇
    1.39
    Activations Density 0.021%

    No Known Activations