© 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. 66811
    Prev
    Next
    INDEX
    Explanations

    nuggets, Nugent, Nuget

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

    The neuron flags metaphorical “bite‐sized” information words—e.g. nuggets or morsels—used to mean small tidbits of wisdom or data.

    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
    e
    -4.47
    i
    -3.64
    }
    -2.77
    or
    -2.75
    m
    -2.73
    p
    -2.70
    o
    -2.63
    a
    -2.59
    as
    -2.59
    il
    -2.55
    POSITIVE LOGITS
    鼍
    2.75
    此事
    2.53
    aimeJ
    2.38
    鸸
    2.38
    <bos>
    2.31
     
    2.28
    觏
    2.28
    
    2.27
     of
    2.23
    𝟭
    2.23
    Activations Density 0.004%

    No Known Activations