© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10872
    Prev
    Next
    INDEX
    Explanations

    go with

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

    The neuron fires on instances of people recommending or choosing something—especially on the “go/going/went with” phrasing in answers.

    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
     TOKYO
    -1.62
    byshire
    -1.42
    Préparation
    -1.41
    şam
    -1.35
    autorelease
    -1.34
     Jefe
    -1.33
    stateParams
    -1.31
    🆘
    -1.31
    Inhoud
    -1.31
     Acne
    -1.31
    POSITIVE LOGITS
     About
    1.74
     a
    1.63
    "
    1.59
    からは
    1.55
     also
    1.52
    also
    1.46
     who
    1.46
    first
    1.43
     usual
    1.41
     Why
    1.40
    Activations Density 0.029%

    No Known Activations