© 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. 72807
    Prev
    Next
    INDEX
    Explanations

    adjectives before nouns

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

    The neuron fires on subjective evaluative language—particularly sentiment-bearing adjectives (and the adverbs or intensifiers that modify them).

    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
     fleuve
    -1.74
     poème
    -1.47
    ᠷ
    -1.39
     printemps
    -1.30
    incón
    -1.23
    liament
    -1.20
     berkualitas
    -1.20
    tería
    -1.19
    isburg
    -1.18
    cets
    -1.18
    POSITIVE LOGITS
    0
    1.55
     от
    1.49
     [
    1.42
     total
    1.41
     *
    1.38
     не
    1.32
    _
    1.32
     всех
    1.29
    /**
    1.24
     time
    1.24
    Activations Density 0.046%

    No Known Activations