© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43366
    Prev
    Next
    INDEX
    Explanations

    berry, fruit, or juice

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

    The neuron detects words related to berries, fruits, and platelets (blood cells).

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

    This neuron activates on occurrences of the word stem “berry,” especially in forms like “berry” or “berries.”

    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
    as
    -4.00
    or
    -2.97
    il
    -2.89
    (
    -2.77
    in
    -2.75
    no
    -2.69
    a
    -2.55
    an
    -2.53
    」
    -2.48
    aw
    -2.41
    POSITIVE LOGITS
    
    2.77
    蹀
    2.59
    儅
    2.59
    鲻
    2.55
    灩
    2.47
    茕
    2.41
    ทั้งหมด
    2.34
    犰
    2.33
    哢
    2.31
    
    2.31
    Activations Density 0.009%

    No Known Activations