© 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. 22-GEMMASCOPE-RES-131K
    7. 26631
    Prev
    Next
    INDEX
    Explanations

    docker, arrest, atlanta

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

    The neuron activates on standalone numeric tokens (digits, version numbers, dates, section numbers, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    autogui
    -1.19
     टीम
    -1.12
     面包
    -1.12
     jugu
    -1.10
     cofre
    -1.09
     Mittelalter
    -1.07
    konstruktion
    -1.07
    🪢
    -1.06
    ANNEL
    -1.05
    =[];
    -1.04
    POSITIVE LOGITS
    haling
    1.39
     usage
    1.31
     behaviour
    1.26
     ſer
    1.26
     but
    1.20
    āciju
    1.16
     fichero
    1.15
    whelming
    1.15
     کرمان
    1.13
     Raceway
    1.12
    Activations Density 0.023%

    No Known Activations