© 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. 22-GEMMASCOPE-RES-131K
    7. 34596
    Prev
    Next
    INDEX
    Explanations

    medical terms and chord names

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

    code and technical notation related to card games and programming languages.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron activates primarily on numeric tokens or sequences of digits.

    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
    urants
    -1.18
    āja
    -1.10
    取り付け
    -1.09
    ystemen
    -1.08
    pout
    -1.06
    ymus
    -1.04
    rals
    -1.04
    himself
    -1.03
    abyte
    -1.02
     Kebijakan
    -1.02
    POSITIVE LOGITS
     campeonato
    1.23
     campionato
    1.20
     verbessert
    1.13
     championnat
    1.12
     possible
    1.12
     maravilhoso
    1.08
     '>=
    1.08
    美味しかった
    1.08
     espírito
    1.06
    ilove
    1.06
    Activations Density 0.002%

    No Known Activations