© 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. 34-GEMMASCOPE-RES-131K
    7. 108560
    Prev
    Next
    INDEX
    Explanations

    design effects

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

    The neuron fires on occurrences of “effect,” “effects,” “affect,” or “affecting” (and their variants).

    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
    
    -0.80
     frutto
    -0.77
     feuer
    -0.72
    encana
    -0.71
     moss
    -0.71
    picion
    -0.71
     Idiot
    -0.71
     posing
    -0.70
     polega
    -0.70
     ANDREW
    -0.70
    POSITIVE LOGITS
    COLL
    0.88
     Wok
    0.76
     Students
    0.75
     notoriety
    0.75
     Effect
    0.75
     RES
    0.73
    luent
    0.73
    `:
    0.72
     célèbre
    0.71
    Students
    0.71
    Activations Density 0.036%

    No Known Activations