© 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. 10-GEMMASCOPE-RES-131K
    7. 45071
    Prev
    Next
    INDEX
    Explanations

    words starting with cy

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

    This neuron detects the two‐letter string “Cy” (e.g. in Cygwin, Cypher, Cygnus, cyberspace, 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
    geſ
    -2.78
    ྅
    -2.58
    歘
    -2.34
    ágenes
    -2.33
     baumwolle
    -2.25
    ⟞
    -2.20
    й
    -2.19
    髕
    -2.17
     dando
    -2.14
    isées
    -2.14
    POSITIVE LOGITS
    }
    3.53
    {
    3.50
    #
    2.83
    All
    2.80
    The
    2.78
    "
    2.78
     This
    2.73
    ",
    2.69
    ..."
    2.67
    !
    2.67
    Activations Density 0.007%

    No Known Activations