© 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. 84641
    Prev
    Next
    INDEX
    Explanations

    successful in actions

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

    The neuron detects constructions expressing success (e.g. “succeeded in,” “successful in,” “succeeds in”) in the text.

    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
    闓
    -1.88
    pecabe
    -1.74
    歃
    -1.73
     możliwość
    -1.68
    ￪
    -1.61
    
    -1.60
     globally
    -1.60
    extendable
    -1.59
    anglicky
    -1.55
    newborn
    -1.55
    POSITIVE LOGITS
    s
    3.20
    n
    2.20
    ic
    1.91
    an
    1.85
    ing
    1.74
    ad
    1.73
    si
    1.73
    ig
    1.69
    id
    1.65
    h
    1.65
    Activations Density 0.020%

    No Known Activations