© 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. 34-GEMMASCOPE-RES-131K
    7. 78187
    Prev
    Next
    INDEX
    Explanations

    freshly made or prepared

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

    The neuron fires on verbs (especially past participles) that describe how something is produced or prepared, as in “cooked,” “made,” “mixed,” or “prepared.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    splice
    -0.80
     '-
    -0.79
    æ
    -0.77
     decorativos
    -0.77
    entire
    -0.76
    álbum
    -0.76
     کنه
    -0.74
     noches
    -0.74
     denna
    -0.74
     diseño
    -0.73
    POSITIVE LOGITS
     fresh
    2.89
    fresh
    2.19
    Fresh
    2.00
     FRESH
    1.96
    FRESH
    1.90
     Fresh
    1.84
     freshly
    1.77
     freshest
    1.70
     daily
    1.64
     freshness
    1.63
    Activations Density 0.024%

    No Known Activations