© 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. 22-GEMMASCOPE-RES-131K
    7. 26132
    Prev
    Next
    INDEX
    Explanations

    default configuration terms

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

    The neuron fires on instances of the literal token “default” (e.g. in variable or setting names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    犼
    -2.84
    簠
    -2.67
    ꔹ
    -2.59
     inept
    -2.45
     представители
    -2.36
    ⎚
    -2.34
     hapless
    -2.33
     umgangssprach
    -2.33
     Когда
    -2.33
     feier
    -2.31
    POSITIVE LOGITS
    ”
    2.59
    However
    2.41
     romero
    2.36
     seems
    2.33
     frito
    2.30
    ൎ
    2.20
    Several
    2.17
    Some
    2.17
    洐
    2.16
    芣
    2.13
    Activations Density 0.017%

    No Known Activations