© 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. 40027
    Prev
    Next
    INDEX
    Explanations

    size and height constraints

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

    The neuron detects tokens that name quantitative limits or dimensions—words like “size,” “height,” “max,” “bound,” “amplitude,” etc.

    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
     détruire
    -0.88
    Suka
    -0.88
    роки
    -0.84
    長の
    -0.84
    Recorder
    -0.84
    luke
    -0.83
    respective
    -0.83
     glú
    -0.81
     enregistrer
    -0.81
     hưởng
    -0.81
    POSITIVE LOGITS
     limit
    0.99
    constraints
    0.97
     allocating
    0.93
     allocated
    0.89
     limitations
    0.87
    嚓
    0.87
     constraints
    0.87
    limit
    0.86
     ограничения
    0.84
     limitaciones
    0.84
    Activations Density 0.011%

    No Known Activations