© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 161
    Prev
    Next
    INDEX
    Explanations

    song titles

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

    The neuron strongly activates on isolated, capitalized single words that serve as section or title headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    The
    0.41
    Festival
    0.38
    THE
    0.37
    FREE
    0.36
    Ра
    0.35
    О
    0.34
     masterpiece
    0.33
    mystery
    0.33
    В
    0.33
    Halloween
    0.33
    POSITIVE LOGITS
     كويس
    0.37
     Nascimento
    0.36
     hypothalamic
    0.35
     namespaces
    0.35
     olduğuna
    0.34
     माइक्रोस
    0.33
     dışında
    0.33
     Sedangkan
    0.33
     वेक्टर
    0.32
     valign
    0.32
    Activations Density 0.001%

    No Known Activations