© 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. 59796
    Prev
    Next
    INDEX
    Explanations

    part-time or part of

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

    The neuron strongly activates on the substring “part” in words (e.g. in compounds like “part‐time” or “part of”).

    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
    صب
    -0.74
    rpm
    -0.71
    约会
    -0.71
    نين
    -0.71
    ized
    -0.70
    たとえば
    -0.70
    本の
    -0.69
    اق
    -0.69
    ？』
    -0.69
    ättning
    -0.69
    POSITIVE LOGITS
    のですね
    0.88
    bahar
    0.86
    time
    0.85
    cipation
    0.85
    polator
    0.84
     zullen
    0.84
    為に
    0.82
    ảy
    0.79
     time
    0.79
     parlak
    0.78
    Activations Density 0.023%

    No Known Activations