© 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. 38768
    Prev
    Next
    INDEX
    Explanations

    successful outcome or result

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

    The neuron specifically detects occurrences of the word “successful” (in any case) indicating a positive outcome.

    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
     The
    -2.61
     insanely
    -2.48
     fantastic
    -2.47
    蠖
    -2.44
     incredibly
    -2.42
     неболь
    -2.39
     terrific
    -2.39
     decidedly
    -2.34
     strikingly
    -2.33
     crucial
    -2.31
    POSITIVE LOGITS
    …”
    2.81
    這
    2.67
    :”
    2.67
    li
    2.66
    that
    2.63
     که
    2.59
     That
    2.56
    我们
    2.42
    我們
    2.42
    Even
    2.41
    Activations Density 0.012%

    No Known Activations