© 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. 128530
    Prev
    Next
    INDEX
    Explanations

    Greek letter phi, Phi Beta Kappa, Phifer

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

    The neuron strongly activates on the substring “Phi,” i.e. tokens containing the sequence P-h-i.

    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
    忸
    -2.69
    癩
    -2.53
    );
    -2.50
    銛
    -2.48
    賒
    -2.44
    先前
    -2.41
    谞
    -2.41
    .).
    -2.41
    祆
    -2.41
    *}{
    -2.39
    POSITIVE LOGITS
    ’
    3.17
    y
    2.98
    (
    2.94
     But
    2.92
    e
    2.72
     '
    2.66
    鱨
    2.50
     WAY
    2.39
     démocr
    2.39
    裡的
    2.31
    Activations Density 0.001%

    No Known Activations