© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117001
    Prev
    Next
    INDEX
    Explanations

    words starting with ph

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

    The neuron is activated by the subword “Ph,” i.e. words beginning with the letters “ph.”

    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
    を
    -1.02
    が
    -0.91
    前は
    -0.77
    知識
    -0.73
     durée
    -0.72
    回数
    -0.71
     Schutz
    -0.69
    なども
    -0.69
     hornblende
    -0.69
    Jeez
    -0.68
    POSITIVE LOGITS
     ph
    1.69
     Ph
    1.59
    Ph
    1.52
    ph
    1.21
    phoned
    1.17
     phishing
    1.17
     phat
    1.16
     phoneNumber
    1.13
     phot
    1.12
     Pharaoh
    1.11
    Activations Density 0.033%

    No Known Activations