© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36154
    Prev
    Next
    INDEX
    Explanations

    definitely and positive

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

    The neuron sharply activates on words inside quoted speech, essentially spotting dialogue or direct quotations.

    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
    Materiale
    -1.05
    はこの
    -0.99
     preuß
    -0.95
    蛲
    -0.94
    })+
    -0.94
     warto
    -0.93
    >';
    -0.92
    مقد
    -0.91
    /}.
    -0.91
    )!=
    -0.90
    POSITIVE LOGITS
     definitely
    1.45
     [
    1.41
     yes
    1.38
     actually
    1.27
     certainly
    1.20
     absolutely
    1.17
    Depends
    1.12
     indeed
    1.03
    śred
    1.02
     ۱۳۹
    0.99
    Activations Density 0.025%

    No Known Activations