© 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. 85354
    Prev
    Next
    INDEX
    Explanations

    Given a

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

    The neuron fires on the word “Given” (as in “Given …”) that introduces a problem’s assumptions or premises.

    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
    {
    -4.13
    y
    -2.70
    ]
    -2.61
    le
    -2.58
    z
    -2.55
    }
    -2.50
    p
    -2.41
    
    -2.41
    </h5>
    -2.30
     was
    -2.23
    POSITIVE LOGITS
    了啊
    2.61
    囖
    2.58
    錞
    2.52
    While
    2.48
    
    2.41
     Surprisingly
    2.33
    寕
    2.31
    During
    2.28
    ௅
    2.22
     Beſ
    2.19
    Activations Density 0.008%

    No Known Activations