© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16116
    Prev
    Next
    INDEX
    Explanations

    code identifiers

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

    The neuron fires whenever it sees a standalone single‐character token (e.g. a lone letter or symbol).

    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
     twij
    -0.89
    Automation
    -0.85
    utile
    -0.82
     Tiber
    -0.81
    kohl
    -0.80
    実
    -0.78
    уза
    -0.76
    📲
    -0.75
    Scissors
    -0.75
     so
    -0.75
    POSITIVE LOGITS
    similar
    0.85
    その他
    0.84
     other
    0.84
    among
    0.83
     andere
    0.83
    uslar
    0.80
     دیگر
    0.77
    尔的
    0.77
     Ausdrücke
    0.77
     Nachmittag
    0.76
    Activations Density 0.017%

    No Known Activations