© 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. 120111
    Prev
    Next
    INDEX
    Explanations

    plant names and parts

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

    names of plants or fruits like "choke", "pear", "ches", "rose", "okra" and similar botanical terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects mentions of plant (or edible plant/fruit) names.

    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
    流畅
    -1.73
    Wann
    -1.68
    deki
    -1.67
    Neben
    -1.66
    哐
    -1.63
    に入った
    -1.62
     économies
    -1.60
    在中国
    -1.59
    Семья
    -1.59
    arbeitung
    -1.55
    POSITIVE LOGITS
    ].
    1.93
    鸶
    1.93
     Tonnen
    1.74
    </b>
    1.73
                
    1.72
     Ordens
    1.72
    MAXN
    1.69
    стор
    1.66
     schwere
    1.64
    נה
    1.63
    Activations Density 0.015%

    No Known Activations