© 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. 43974
    Prev
    Next
    INDEX
    Explanations

    cull, glean, Sully

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

    The neuron fires on any token containing the letter sequence “cul” (e.g. cull, culled, culls, cullet).

    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
     Undoubtedly
    -2.42
    In
    -2.41
    .
    -2.36
     Ironically
    -2.33
     {
    -2.27
     Sadly
    -2.23
    </i>
    -2.20
     Through
    -2.17
     Providing
    -2.17
     Perhaps
    -2.08
    POSITIVE LOGITS
     schal
    2.56
     背影
    2.52
    薆
    2.47
     possono
    2.36
    亖
    2.33
    ܞ
    2.30
    ￪
    2.23
     treu
    2.22
     gewi
    2.19
     erhi
    2.17
    Activations Density 0.004%

    No Known Activations