© 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. 105643
    Prev
    Next
    INDEX
    Explanations

    point out or point me

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

    The neuron activates on occurrences of the word “point.”

    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
     what
    -2.30
    閬
    -2.14
     ONLY
    -2.09
    雳
    -2.05
     edgy
    -2.02
    在此
    -1.95
    >
    -1.94
    ))));
    -1.93
    i
    -1.92
     dalam
    -1.87
    POSITIVE LOGITS
    犼
    2.67
    ቺ
    2.52
    そういえば
    2.50
     anuncia
    2.47
    ೢ
    2.45
     pérd
    2.44
    毉
    2.42
    駡
    2.41
    拍了
    2.39
    乄
    2.39
    Activations Density 0.012%

    No Known Activations