© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84460
    Prev
    Next
    INDEX
    Explanations

    our services and products

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

    The neuron fires strongly on marketing‐style descriptive copy—i.e. promotional language listing benefits, features, or welcomes.

    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
    😷
    -1.31
     キット
    -1.16
     haba
    -1.16
    😡
    -1.16
     kaos
    -1.16
    👿
    -1.15
     poliuret
    -1.14
     Abbé
    -1.14
     Tugas
    -1.11
    tså
    -1.10
    POSITIVE LOGITS
     your
    1.59
     you
    1.25
     ит
    1.23
    🧫
    1.19
    我跟
    1.15
     our
    1.14
     klicken
    1.13
     Our
    1.13
     také
    1.12
     okolí
    1.12
    Activations Density 0.045%

    No Known Activations