© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99215
    Prev
    Next
    INDEX
    Explanations

    heap or heel

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

    The neuron activates whenever it sees the token “heap.”

    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
    红的
    -0.93
    čkou
    -0.87
     gän
    -0.86
    fmf
    -0.85
    trina
    -0.85
    ሎ
    -0.83
    haji
    -0.83
    (=)
    -0.82
    entee
    -0.81
     öffentlich
    -0.81
    POSITIVE LOGITS
    sort
    1.08
     ​​
    0.90
     wys
    0.88
    なども
    0.86
     Januar
    0.84
    ys
    0.84
    ('*',
    0.84
     Ο
    0.83
    ily
    0.82
    独特
    0.82
    Activations Density 0.004%

    No Known Activations