© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14249
    Prev
    Next
    INDEX
    Explanations

    reporting spoken words

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

    The neuron flags reporting verbs (like “says” or “said”) that attribute spoken quotes.

    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
    u
    -1.68
     and
    -1.66
    and
    -1.48
    er
    -1.48
    el
    -1.48
    Y
    -1.47
    e
    -1.40
     /
    -1.39
     where
    -1.38
    al
    -1.36
    POSITIVE LOGITS
     菇
    1.55
     portugués
    1.52
    twas
    1.45
    
    1.45
     egenskaper
    1.43
     Física
    1.41
     werkt
    1.40
     ajout
    1.39
     RIVERS
    1.39
     BRUN
    1.37
    Activations Density 0.014%

    No Known Activations