© 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. 10-GEMMASCOPE-RES-131K
    7. 14843
    Prev
    Next
    INDEX
    Explanations

    song titles and lengths

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

    The neuron activates on colon characters used as delimiters in numerical time or score notations (e.g., “3:16” or “42:23”).

    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
    s
    -1.66
    is
    -1.64
    in
    -1.52
    “
    -1.49
    稔
    -1.46
     tentativo
    -1.45
    🙁
    -1.45
     is
    -1.44
    (;;)
    -1.40
     総合
    -1.40
    POSITIVE LOGITS
    回来的
    1.73
    mbgg
    1.63
    ケモン
    1.58
    continu
    1.57
    pompa
    1.55
    đầm
    1.53
     montagnes
    1.53
    giày
    1.50
    autogui
    1.50
    艄
    1.47
    Activations Density 0.009%

    No Known Activations