© 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. 99578
    Prev
    Next
    INDEX
    Explanations

    absolute, unconditional, or complete states

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

    The neuron fires on words that express absolute or total states—strong intensifiers like “absolute,” “unconditional,” “total,” “guarantee,” “control,” and the like.

    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
     Selecciona
    -1.35
    Gears
    -1.34
    kwür
    -1.31
     yor
    -1.30
    APY
    -1.28
    encore
    -1.28
    weiterlesen
    -1.27
    près
    -1.27
    Jeans
    -1.25
     Añade
    -1.24
    POSITIVE LOGITS
     there
    1.95
    There
    1.89
    If
    1.74
    From
    1.74
     that
    1.73
    //
    1.67
    Maybe
    1.60
    When
    1.58
    when
    1.54
    All
    1.52
    Activations Density 0.094%

    No Known Activations