© 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. 22-GEMMASCOPE-RES-131K
    4. 128999
    Prev
    Next
    INDEX
    Explanations

    The neuron flags section headers or titles—short, standalone lines (often in title case or uppercase) that introduce or label a block of content.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    free and easy

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     menyen
    -1.22
     signifikan
    -1.16
    Serviço
    -1.13
    inerario
    -1.10
     hochwertige
    -1.10
    Dicas
    -1.09
     ибо
    -1.08
     treff
    -1.07
     nimmer
    -1.07
     kontinu
    -1.06
    POSITIVE LOGITS
    !
    3.08
    !"
    2.11
    !”
    2.00
    !)
    1.95
    !’
    1.77
    !}
    1.75
    !");
    1.73
    !</
    1.66
     our
    1.65
    !).
    1.62
    Activations Density 0.099%

    No Known Activations