© 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. 34-GEMMASCOPE-RES-131K
    7. 57141
    Prev
    Next
    INDEX
    Explanations

    success and outcomes

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

    The neuron strongly activates on words that report or quantify outcomes or results (e.g. “found,” “mixed,” “success”).

    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
    smithy
    -0.91
    ynı
    -0.88
     gương
    -0.86
    ţei
    -0.86
     olo
    -0.85
     RouterModule
    -0.82
    был
    -0.82
     censiti
    -0.81
    icamente
    -0.81
     tille
    -0.81
    POSITIVE LOGITS
     success
    6.09
    success
    4.47
    Success
    3.94
     Success
    3.88
     éxito
    3.67
     successes
    3.56
     sucesso
    3.22
     успех
    3.03
     Erfolg
    3.02
     SUCCESS
    3.00
    Activations Density 0.071%

    No Known Activations