© 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. 84618
    Prev
    Next
    INDEX
    Explanations

    affirmative action

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

    This neuron activates on occurrences of the root “affirm,” including its verb forms (affirm, affirming, affirmed) and the adjective “affirmative.”

    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
    bluza
    -2.44
     οι
    -2.41
    簠
    -2.28
     مختلفة
    -2.28
    Ꮣ
    -2.22
     tetapi
    -2.20
     欣赏
    -2.19
     pomoci
    -2.14
     crí
    -2.11
    strona
    -2.11
    POSITIVE LOGITS
    呖
    4.00
    h
    2.91
    e
    2.86
    n
    2.84
    </h3>
    2.64
    l
    2.61
    
    2.56
    ский
    2.55
    ”:
    2.53
    ↵
    2.47
    Activations Density 0.001%

    No Known Activations