© 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. 10-GEMMASCOPE-RES-131K
    7. 104565
    Prev
    Next
    INDEX
    Explanations

    Boone and devoid of

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

    The neuron strongly activates on low‐frequency, uncommon or specialized words (including proper names and technical terms).

    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
    er
    -4.00
    “
    -3.63
    '
    -3.25
     
    -3.19
    ?
    -2.95
    is
    -2.64
    ”,
    -2.64
    嵙
    -2.56
    man
    -2.53
    h
    -2.53
    POSITIVE LOGITS
    埽
    3.36
    ሖ
    3.27
    ндарт
    2.95
    ꯸
    2.78
    泐
    2.58
     стоковые
    2.58
    玙
    2.53
    ﱠ
    2.50
    ᄍ
    2.48
    纐
    2.44
    Activations Density 0.019%

    No Known Activations