© 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. 34-GEMMASCOPE-RES-131K
    7. 82650
    Prev
    Next
    INDEX
    Explanations

    young animals and immature stages

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

    references to young animals or offspring, particularly in scientific or news contexts.

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

    The neuron activates on numeric expressions and quantitative measurements (numbers, units, counts).

    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
    teacher
    -0.80
     cancers
    -0.79
    teachers
    -0.74
     человек
    -0.73
     DOGS
    -0.72
    惊讶
    -0.72
    震惊
    -0.72
     дочь
    -0.71
    阕
    -0.71
    ンドル
    -0.70
    POSITIVE LOGITS
     young
    3.38
     juvenile
    2.78
     baby
    2.73
     seedlings
    2.61
     newborn
    2.58
     infant
    2.44
     juveniles
    2.44
    幼
    2.42
     larvae
    2.38
    young
    2.34
    Activations Density 0.216%

    No Known Activations