© 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. 28214
    Prev
    Next
    INDEX
    Explanations

    reusable, permanent, or default

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

    The neuron is tuned to spot tokens in bulk‐meal or batch‐cooking recipe instructions (e.g. preparing, making, keeping food in bulk).

    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
     пыта
    -0.91
     deportivas
    -0.90
     apparaît
    -0.86
    ENSATION
    -0.86
    dova
    -0.85
     intentar
    -0.84
     opposed
    -0.84
     its
    -0.84
     eneste
    -0.84
    ocusing
    -0.82
    POSITIVE LOGITS
     for
    1.54
    reusable
    1.43
     reusable
    1.30
     permanent
    1.30
    Reusable
    1.28
     permanente
    1.20
     Reusable
    1.11
    Permanent
    1.10
     постоян
    1.09
     Permanent
    1.05
    Activations Density 0.134%

    No Known Activations