© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71720
    Prev
    Next
    INDEX
    Explanations

    Jayhawk

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

    The neuron detects author bylines or signature blocks, i.e. personal names in the document headers or footers.

    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
     Quận
    -1.44
     to
    -1.43
    atche
    -1.35
    Ե
    -1.32
    EFIAPI
    -1.32
     into
    -1.32
    ESOME
    -1.31
    榛
    -1.30
    Nhà
    -1.27
    kraine
    -1.26
    POSITIVE LOGITS
     have
    1.81
     want
    1.71
    0
    1.58
    5
    1.54
    1
    1.52
    3
    1.34
    .".
    1.34
    hline
    1.34
    un
    1.33
    am
    1.30
    Activations Density 0.014%

    No Known Activations