© 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. 34-GEMMASCOPE-RES-131K
    7. 25785
    Prev
    Next
    INDEX
    Explanations

    veiled shot, jab, Q:

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

    The neuron detects figurative “shooting” or “firing” metaphors used to signal an attack or rebuttal (e.g. “takes a shot at,” “fires back”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     cory
    -0.83
    Жан
    -0.80
    rste
    -0.75
     lumineux
    -0.75
    RequestId
    -0.72
     nera
    -0.71
     KANSAS
    -0.71
    Beste
    -0.71
    RequestMapping
    -0.71
     sedu
    -0.70
    POSITIVE LOGITS
     jab
    1.91
     swipe
    1.76
     indirect
    1.69
     shots
    1.65
     shade
    1.63
     digs
    1.55
    Shade
    1.52
     indirectly
    1.50
     Indirect
    1.46
    Shots
    1.42
    Activations Density 0.031%

    No Known Activations