© 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. 10-GEMMASCOPE-RES-131K
    7. 103484
    Prev
    Next
    INDEX
    Explanations

    input to or store coordinator

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

    This neuron lights up on uncommon, domain‐specific or technical terms (i.e. low‐frequency jargon across biology, computing, law, 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_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
     geene
    -1.57
     certaines
    -1.54
     Danemark
    -1.53
     Receives
    -1.49
     carrito
    -1.48
     seksi
    -1.48
     trein
    -1.47
     aluno
    -1.46
     Announces
    -1.46
     pourront
    -1.45
    POSITIVE LOGITS
     In
    1.81
     on
    1.65
     help
    1.63
     in
    1.62
     FOR
    1.52
     to
    1.51
     or
    1.51
     problems
    1.48
     find
    1.44
     Since
    1.44
    Activations Density 0.127%

    No Known Activations