© 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. 22-GEMMASCOPE-RES-131K
    7. 15797
    Prev
    Next
    INDEX
    Explanations

    intensifier + adjective/adverb

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

    The neuron strongly lights up on emphatic intensifiers—especially “very” (and similar boost words like “sooo,” “long”, etc.) used to add emphasis.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     ekos
    -1.88
     maksi
    -1.83
     aspek
    -1.82
    swire
    -1.77
     pittores
    -1.73
     panik
    -1.73
     restoran
    -1.73
    itisation
    -1.70
     komik
    -1.66
     skru
    -1.66
    POSITIVE LOGITS
    ,
    2.34
    '
    1.89
    -
    1.83
    They
    1.65
     they
    1.55
    ’
    1.45
     no
    1.41
     not
    1.41
     They
    1.37
    _
    1.37
    Activations Density 0.035%

    No Known Activations