© 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. 130075
    Prev
    Next
    INDEX
    Explanations

    alot

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

    This neuron detects the nonstandard “a lot” spelling (tokens like “alot” or “allot”).

    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
    }
    -2.44
    s
    -2.36
     продукти
    -2.25
     him
    -2.19
    ar
    -2.09
    拶
    -2.08
    푣
    -2.06
    m
    -2.03
    a
    -2.02
     stately
    -1.98
    POSITIVE LOGITS
    They
    3.17
    This
    2.64
    Their
    2.61
    ſu
    2.50
     "...
    2.48
    읗
    2.41
    These
    2.41
    '"
    2.38
    𓐍
    2.34
    "'
    2.31
    Activations Density 0.001%

    No Known Activations