© 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. 8429
    Prev
    Next
    INDEX
    Explanations

    Meredith, McCartney, permalink, continuum, Palau

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

    The neuron responds to capitalized proper nouns—especially personal and place names.

    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
    ꔹ
    -3.08
    辄
    -2.69
    翃
    -2.64
    био
    -2.56
    ৢ
    -2.42
    ſche
    -2.41
     Pastikan
    -2.33
    unjungi
    -2.33
     无
    -2.30
     We
    -2.27
    POSITIVE LOGITS
    .”
    3.27
    s
    3.03
    ’
    2.88
    h
    2.58
    '
    2.42
    ，“
    2.31
    (“
    2.23
    rl
    2.16
     “
    2.16
    they
    2.13
    Activations Density 0.004%

    No Known Activations