© 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. 102818
    Prev
    Next
    INDEX
    Explanations

    written on

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

    The neuron detects mentions of writing or written text placed on a surface (e.g. “written on,” “write name on,” “written across”).

    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
    The
    -2.08
     completos
    -1.46
    This
    -1.43
    Our
    -1.43
    (
    -1.41
     doesn
    -1.30
     נ
    -1.30
     me
    -1.28
    {
    -1.27
    ]
    -1.27
    POSITIVE LOGITS
     berühmten
    1.34
     genellikle
    1.34
     membentuk
    1.32
    ेशा
    1.27
     preva
    1.23
     spesielt
    1.23
    内容は
    1.22
     специальные
    1.22
    Зно
    1.21
     unce
    1.21
    Activations Density 0.026%

    No Known Activations