© 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. 10-GEMMASCOPE-RES-131K
    7. 65205
    Prev
    Next
    INDEX
    Explanations

    second derivative of

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

    The neuron flags specialized technical or scientific terminology (especially field‐specific nouns) found in academic or mathematical contexts.

    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
    pherds
    -1.68
     الشرطة
    -1.64
     perfe
    -1.57
    
    -1.55
    EVEN
    -1.49
     ARISING
    -1.48
     diſ
    -1.48
    siah
    -1.45
    featuring
    -1.45
     direc
    -1.43
    POSITIVE LOGITS
     that
    2.92
     while
    2.45
     this
    2.31
     which
    2.00
     during
    1.77
     if
    1.72
     from
    1.71
     any
    1.70
     at
    1.64
     our
    1.64
    Activations Density 0.053%

    No Known Activations