© 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. 70611
    Prev
    Next
    INDEX
    Explanations

    titles and dates

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

    The neuron activates on camel-case configuration property names (e.g. styleUrls, templateUrl, aliases, typeRoots).

    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
    Mesmo
    -1.07
     smtplib
    -1.02
    Poznám
    -0.99
     setDescription
    -0.96
     anyone
    -0.96
    Zubereitung
    -0.96
    Elaboración
    -0.95
     still
    -0.95
    Ainda
    -0.95
    Tienes
    -0.94
    POSITIVE LOGITS
    сколько
    1.10
     and
    0.98
     उन्ह
    0.91
     каждого
    0.91
     придется
    0.87
     tutaj
    0.86
    ceff
    0.85
    ставля
    0.85
    四个
    0.85
     ua
    0.84
    Activations Density 0.000%

    No Known Activations