© 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. 45344
    Prev
    Next
    INDEX
    Explanations

    generalization and extension

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

    The neuron responds to high-level academic “action” verbs (introduce, prove, derive, show, discuss, generalize, etc.) that describe methods or contributions in scientific writing.

    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
     vélos
    -0.90
    ])/
    -0.80
     Molina
    -0.80
    strix
    -0.76
     первых
    -0.75
    カス
    -0.75
    favorable
    -0.72
    知道的
    -0.72
    bantu
    -0.72
    atists
    -0.72
    POSITIVE LOGITS
     generalization
    3.94
     generalizations
    3.53
     generalize
    3.31
     extension
    3.28
     extensions
    3.06
     extend
    2.92
     extending
    2.78
     extends
    2.64
    extension
    2.58
    Extension
    2.52
    Activations Density 0.138%

    No Known Activations