© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101090
    Prev
    Next
    INDEX
    Explanations

    turf and mulch

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

    The neuron strongly activates on occurrences of the word “turf” (i.e. references to turf/ground surface).

    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
     —
    -3.06
    餿
    -2.83
    艄
    -2.72
    翾
    -2.70
    р
    -2.70
    </td>
    -2.69
    舠
    -2.56
    痦
    -2.55
    '];
    -2.48
    玧
    -2.44
    POSITIVE LOGITS
    是非常
    2.58
    ;
    2.23
    '
    2.22
     turf
    2.17
    是個
    2.16
     of
    2.13
     diffe
    2.09
    ╿
    2.09
    是很
    2.05
    Kondisi
    2.05
    Activations Density 0.003%

    No Known Activations