© 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. 34-GEMMASCOPE-RES-131K
    7. 63105
    Prev
    Next
    INDEX
    Explanations

    political figures and people

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

    This neuron strongly activates on capitalized proper names (especially people’s surnames and other named entities).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    their
    -1.39
    PYX
    -1.34
    -};
    -1.31
     אך
    -1.19
    moreland
    -1.17
    igth
    -1.17
    蟆
    -1.13
    nemers
    -1.13
     Qaraldi
    -1.12
     honn
    -1.09
    POSITIVE LOGITS
     certainly
    2.45
     may
    2.28
     might
    2.17
     isn
    2.03
     obviously
    1.88
     wasn
    1.86
     didn
    1.76
     seems
    1.73
     definitely
    1.64
    의
    1.58
    Activations Density 0.089%

    No Known Activations