© 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. 34-GEMMASCOPE-RES-131K
    7. 79075
    Prev
    Next
    INDEX
    Explanations

    Copyright and family

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

    The neuron is attuned to tokens containing digits (i.e. any numeric literals or numbers).

    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
     barne
    -1.00
     réponse
    -0.99
     عندما
    -0.96
     piden
    -0.94
     هذا
    -0.92
    圖
    -0.91
     récemment
    -0.91
     PUBLICATIONS
    -0.90
     incendie
    -0.89
     espécies
    -0.88
    POSITIVE LOGITS
     listening
    1.20
     and
    1.13
     listen
    1.11
     Listen
    1.09
     console
    1.08
    Listen
    1.07
    console
    1.03
     Listening
    1.02
     with
    0.92
    listen
    0.92
    Activations Density 0.002%

    No Known Activations