© 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. 39605
    Prev
    Next
    INDEX
    Explanations

    with all the

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

    This neuron is highly activated by the quantifier “all” (especially in phrases like “with all …”).

    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
    ’
    -2.91
     there
    -1.80
    So
    -1.75
     has
    -1.75
     seems
    -1.73
    𓆜
    -1.73
     wasn
    -1.72
    ając
    -1.72
     was
    -1.70
    よく
    -1.70
    POSITIVE LOGITS
     regard
    3.02
    stood
    2.72
     regards
    2.50
    standing
    2.47
    珦
    2.19
     behulp
    2.16
     whom
    2.16
     και
    2.14
     frecuencia
    2.11
     respect
    2.05
    Activations Density 0.007%

    No Known Activations