© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20416
    Prev
    Next
    INDEX
    Explanations

    behavioral analysis

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

    The neuron is tuned to detect mentions of “behavior” (including its variants like “behaviour” and “behaviors”).

    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
     '</
    -1.51
    alties
    -1.38
    ician
    -1.30
    ſtion
    -1.25
    例如
    -1.25
    Matic
    -1.23
    hetta
    -1.23
     дешевле
    -1.23
    ztes
    -1.21
     '=
    -1.20
    POSITIVE LOGITS
     on
    1.88
     patterns
    1.64
     their
    1.54
     choose
    1.51
     behavior
    1.49
     through
    1.49
     chooses
    1.49
     data
    1.41
     trends
    1.32
     different
    1.30
    Activations Density 0.088%

    No Known Activations