© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8199
    Prev
    Next
    INDEX
    Explanations

    code structure

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

    The neuron flags literal numbers in code (numeric constants).

    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
     a
    -2.02
     of
    -1.72
    _
    -1.52
    section
    -1.49
    /
    -1.48
     part
    -1.48
    )};
    -1.47
     B
    -1.43
    :
    -1.38
     your
    -1.34
    POSITIVE LOGITS
    iamo
    1.65
    它
    1.62
    </h5>
    1.58
     they
    1.57
     it
    1.55
    Materiale
    1.53
     estekak
    1.51
    Stap
    1.50
    titial
    1.49
    Минусы
    1.47
    Activations Density 0.021%

    No Known Activations