© 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. 10-GEMMASCOPE-RES-131K
    7. 100520
    Prev
    Next
    INDEX
    Explanations

    abundance or plenty

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

    This neuron detects words that express abundance or plentifulness (e.g. “abound,” “abounds,” “galore”).

    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
    ⚋
    -2.80
    ꔹ
    -2.52
     combinar
    -2.44
    迓
    -2.39
     tracción
    -2.38
    ⚥
    -2.31
     queridos
    -2.30
    силання
    -2.27
    蜴
    -2.23
    蟜
    -2.14
    POSITIVE LOGITS
    ers
    2.63
    t
    2.53
    *
    2.50
    –
    2.44
    AN
    2.44
    ,"
    2.38
     been
    2.27
    ت
    2.19
    l
    2.11
    n
    2.09
    Activations Density 0.003%

    No Known Activations