© 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. 111866
    Prev
    Next
    INDEX
    Explanations

    Fisher names and terms

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

    The neuron strongly responds to occurrences of the capitalized token “Fisher.”

    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
    蕺
    -3.16
    ’
    -2.80
    檍
    -2.69
    퐹
    -2.67
    鼍
    -2.67
     soooo
    -2.59
     exceptionally
    -2.55
     exhilarating
    -2.50
     amazingly
    -2.48
    ⬈
    -2.45
    POSITIVE LOGITS
    when
    2.77
    </i>
    2.73
    ⎽
    2.70
     When
    2.61
    That
    2.52
    9
    2.50
    2
    2.42
    When
    2.42
     她
    2.38
     需要
    2.34
    Activations Density 0.005%

    No Known Activations