© 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. 69409
    Prev
    Next
    INDEX
    Explanations

    not followed by verb

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

    This neuron responds to common English function words—especially auxiliaries and negations like “to,” “not,” “be,” 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
    <>();
    
    -1.53
     where
    -1.46
    </em>
    -1.43
     mutta
    -1.42
    );
    -1.42
    </h2>
    -1.41
     kuten
    -1.40
     där
    -1.36
     of
    -1.35
    ());
    -1.31
    POSITIVE LOGITS
    Decent
    1.55
     можна
    1.48
    ſons
    1.30
    基本
    1.29
     fossero
    1.27
    亅
    1.23
     sarebbe
    1.22
     atleast
    1.21
     idyl
    1.21
    
    1.20
    Activations Density 0.043%

    No Known Activations