© 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. 2980
    Prev
    Next
    INDEX
    Explanations

    of functions

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

    The neuron fires on story‐synopsis or plot‐introduction phrasing (e.g. “is the tale of…”) that introduces a narrative summary.

    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
    <unused2130>
    0.57
    <unused2172>
    0.50
     advisable
    0.49
     вам
    0.48
    <unused2164>
    0.48
     ваше
    0.46
    <unused2173>
    0.46
    <unused2137>
    0.46
    <unused2121>
    0.45
    <unused2117>
    0.45
    POSITIVE LOGITS
     Gegensatz
    0.52
     Ünivers
    0.51
     Announces
    0.50
     Büyük
    0.50
     The
    0.49
     Executive
    0.49
     Pat
    0.48
     Two
    0.47
     Relations
    0.47
     Dialog
    0.47
    Activations Density 0.080%

    No Known Activations