© 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. 67669
    Prev
    Next
    INDEX
    Explanations

    HARTFORD, Chino, Sencha, Q, Constructable

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

    This neuron activates on square-bracketed annotation tokens (e.g. “[Constructible]” or “[begin_description]”).

    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
     its
    -1.56
    贋
    -1.48
     it
    -1.39
     everything
    -1.34
     many
    -1.33
     them
    -1.31
     some
    -1.31
     all
    -1.30
     gwaran
    -1.30
     “
    -1.30
    POSITIVE LOGITS
    </em>
    1.88
     herrera
    1.48
     [''],
    1.42
     '')
    1.38
    u
    1.34
    k
    1.33
     européens
    1.30
     ''
    1.28
     attuale
    1.27
     schuhe
    1.25
    Activations Density 0.000%

    No Known Activations