© 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. 10-GEMMASCOPE-RES-131K
    7. 69793
    Prev
    Next
    INDEX
    Explanations

    beat

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

    The neuron detects occurrences of the word “beat” (in any form or casing, including “beats”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    .”
    -2.44
    .“
    -2.28
    
    -2.19
    鱻
    -2.19
     чрез
    -2.17
    ୈ
    -2.13
    j
    -2.05
    女性の
    -2.03
    斂
    -2.03
    ፨
    -2.02
    POSITIVE LOGITS
    '
    4.34
    {
    2.58
    warnai
    2.25
     étaient
    2.17
    ᩠
    2.02
     impede
    2.02
     What
    1.94
    衄
    1.93
     erne
    1.89
    S
    1.89
    Activations Density 0.006%

    No Known Activations