© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70598
    Prev
    Next
    INDEX
    Explanations

    uniform context

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

    The neuron flags mentions of numeric product details (sizes, models, counts, etc.) in commercial or promotional text.

    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
     their
    -1.57
     in
    -1.47
     on
    -1.31
     new
    -1.30
     бампер
    -1.29
     to
    -1.27
     young
    -1.24
     sehr
    -1.18
     they
    -1.16
     our
    -1.16
    POSITIVE LOGITS
     musées
    1.32
    ἵ
    1.28
     Rabatt
    1.23
    ękuję
    1.22
     bestselling
    1.21
    nehå
    1.20
     produisent
    1.19
    σετε
    1.18
     indeb
    1.17
    onekana
    1.17
    Activations Density 0.001%

    No Known Activations