© 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. 34-GEMMASCOPE-RES-131K
    7. 915
    Prev
    Next
    INDEX
    Explanations

    Curb Appeal, shelf life, reported film

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

    The neuron selectively fires on tokens containing “curb” (e.g. curb, curbs, curbside).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ров
    -0.73
    bourn
    -0.68
     CONTACT
    -0.68
    黨
    -0.67
     màn
    -0.65
     Garfield
    -0.65
    tidae
    -0.65
     편
    -0.64
    жность
    -0.63
    WidgetItem
    -0.63
    POSITIVE LOGITS
     sacraments
    0.68
    OMEM
    0.68
    家に
    0.67
     Castle
    0.67
     hell
    0.66
     reserv
    0.66
    軟體
    0.66
    體
    0.65
     completes
    0.65
     شنا
    0.64
    Activations Density 0.045%

    No Known Activations