© 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. 1797
    Prev
    Next
    INDEX
    Explanations

    dedication to or focus on

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

    The neuron activates on numeric tokens—particularly multi‐digit numbers like years or large counts—highlighting when the text contains explicit numerical values.

    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
     embracing
    -1.06
     all
    -1.02
     través
    -0.96
     always
    -0.96
     had
    -0.91
     melalui
    -0.90
    encia
    -0.90
     士
    -0.89
    чера
    -0.88
    ními
    -0.86
    POSITIVE LOGITS
     to
    2.11
     towards
    1.88
     toward
    1.61
     into
    1.48
    towards
    1.44
    toward
    1.18
    เพื่อ
    1.13
     darauf
    1.00
     Towards
    0.92
    formerly
    0.91
    Activations Density 0.032%

    No Known Activations