© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2305
    Prev
    Next
    INDEX
    Explanations

    the end

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

    The neuron fires on temporal expressions—especially prepositional phrases that mark specific times or deadlines (e.g. “For the first time,” “By the end of May/June,” “middle of this year”).

    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_31_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
     history
    0.56
     এতদিন
    0.55
    Possibly
    0.55
     इतिहास
    0.54
    ancer
    0.54
    ções
    0.53
    atov
    0.53
    <unused83>
    0.52
    ancers
    0.52
     aprender
    0.52
    POSITIVE LOGITS
     end
    0.74
    inizio
    0.71
     onset
    0.69
    beginning
    0.69
     midpoint
    0.68
     eve
    0.66
     outset
    0.66
    arrival
    0.65
    onset
    0.65
     beginning
    0.63
    Activations Density 0.254%

    No Known Activations