© 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. 34-GEMMASCOPE-RES-131K
    7. 107054
    Prev
    Next
    INDEX
    Explanations

    sizes, sizes, sizes

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

    The neuron activates on tokens containing the character sequence “int.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     antagonism
    -0.73
    ritos
    -0.70
     tvor
    -0.69
     najdete
    -0.68
    llen
    -0.68
     whether
    -0.68
    AndPassword
    -0.67
    Cassandra
    -0.66
     vzor
    -0.66
    ůli
    -0.66
    POSITIVE LOGITS
    Size
    0.94
    サイズ
    0.87
     Size
    0.87
     SIZE
    0.87
    camiento
    0.79
    ukuran
    0.77
     Millar
    0.75
    getSize
    0.73
     getSize
    0.73
    sized
    0.72
    Activations Density 0.024%

    No Known Activations