© 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. 58559
    Prev
    Next
    INDEX
    Explanations

    adjectives, intensifiers

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

    The neuron is detecting emphatic intensifiers and superlative‐style modifiers (e.g. “super-effective,” “absolutely,” “biggest,” “gosh-darnedest,” etc.).

    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
     to
    -1.41
    などで
    -1.34
     kolejny
    -1.31
     ktorí
    -1.23
     sharper
    -1.23
     ولی
    -1.20
    生活的
    -1.20
     obyvateľov
    -1.18
     Inhalten
    -1.16
     célèbre
    -1.16
    POSITIVE LOGITS
     people
    1.45
    astră
    1.42
    Only
    1.37
     TRABAJO
    1.34
     plátano
    1.34
    ATIONS
    1.29
     Nota
    1.29
     awful
    1.29
     Jetzt
    1.27
    区的
    1.23
    Activations Density 0.058%

    No Known Activations