© 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. 84416
    Prev
    Next
    INDEX
    Explanations

    greek letter phi

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

    This neuron activates on occurrences of the sequence “phi” (e.g. in names like Phi or phi).

    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
    哢
    -2.31
     müssen
    -2.31
     оценка
    -2.30
    𞤢
    -2.30
    $
    -2.28
    the
    -2.25
     хорошая
    -2.25
     todėl
    -2.22
    鹮
    -2.16
    尨
    -2.16
    POSITIVE LOGITS
    埽
    2.50
     lança
    2.45
    ’
    2.34
     /
    2.25
    蟊
    2.19
     During
    2.17
    
    2.17
     It
    2.11
     But
    2.09
     apresenta
    2.09
    Activations Density 0.005%

    No Known Activations