© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39129
    Prev
    Next
    INDEX
    Explanations

    scope of coverage

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

    The neuron is primarily keyed to the word “scope” (and its close numeric qualifiers), activating strongly whenever “scope” appears.

    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
     Obtén
    -1.25
     pasaba
    -1.17
    حص
    -1.14
    absch
    -1.12
     toneladas
    -1.10
     sentía
    -1.09
    .
    -1.09
    "));
    -1.09
     trouva
    -1.09
    为什么
    -1.05
    POSITIVE LOGITS
     scope
    2.08
     of
    1.72
     coverage
    1.68
     range
    1.63
    scope
    1.58
     broader
    1.43
     breadth
    1.42
     Scope
    1.40
     and
    1.34
    Scope
    1.31
    Activations Density 0.052%

    No Known Activations