© 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. 72882
    Prev
    Next
    INDEX
    Explanations

    file paths and url paths

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

    The neuron flags string literals beginning with a forward slash (i.e. the '"/' sequence in code).

    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
    </h3>
    -3.27
    呖
    -2.48
    "
    -2.39
     ܙ
    -2.31
    ?».
    -2.28
     When
    -2.22
    衕
    -2.22
    薷
    -2.20
    chengladbach
    -2.19
    思议
    -2.19
    POSITIVE LOGITS
    6
    2.88
    5
    2.78
    </b>
    2.66
    很是
    2.64
    an
    2.58
    7
    2.56
    ان
    2.56
     {
    2.50
     étab
    2.45
     шести
    2.42
    Activations Density 0.009%

    No Known Activations