© 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. 44878
    Prev
    Next
    INDEX
    Explanations

    cluster contexts

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

    The neuron activates strongly on occurrences of the word “cluster” (in any capitalization).

    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
    ᨒ
    -3.25
    ꦧ
    -2.88
    癀
    -2.86
    鰨
    -2.78
    쫀
    -2.75
    毳
    -2.73
    
    -2.69
    ᠌
    -2.69
    廰
    -2.63
     patrie
    -2.58
    POSITIVE LOGITS
    ;
    2.98
    ...
    2.89
    <td>
    2.83
    \
    2.78
    at
    2.64
    _
    2.64
    [
    2.53
    “
    2.53
    :
    2.50
    ]
    2.47
    Activations Density 0.006%

    No Known Activations