© 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. 26669
    Prev
    Next
    INDEX
    Explanations

    OpenFOAM, Court titles, Legal terms

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

    The neuron responds to standalone uppercase letters (e.g. individual acronym or header initials).

    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
     in
    -1.57
    quelize
    -1.27
     did
    -1.15
    などの
    -1.13
     should
    -1.11
     other
    -1.11
     on
    -1.10
     japonesa
    -1.10
    TRIBUN
    -1.09
     has
    -1.06
    POSITIVE LOGITS
     to
    1.41
     jednej
    1.29
     semelh
    1.23
     légèrement
    1.23
    /#{
    1.20
     combustível
    1.20
    inery
    1.19
     Bedürf
    1.16
     a
    1.14
    lograph
    1.12
    Activations Density 0.007%

    No Known Activations