© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 173
    Prev
    Next
    INDEX
    Explanations

    statistics, numbers, policy

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

    The neuron spikes at the boundaries of long, instructional paragraphs—i.e. it detects the end‐of‐chunk/paragraph marker when the preceding segment is an extended block of procedural or explanatory text.

    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
     возле
    0.54
     প্রথমে
    0.52
     ০১
    0.52
     মোঃ
    0.49
     गुरूवार
    0.48
     منطقة
    0.47
     முதலில்
    0.47
    𓂃
    0.46
     மற்றும்
    0.46
     இவர்
    0.45
    POSITIVE LOGITS
     conceivably
    0.52
     capitalismo
    0.51
     unambiguously
    0.50
     postmodern
    0.49
     saurait
    0.48
    そういう
    0.48
     durchaus
    0.48
     manifestly
    0.48
    こうした
    0.48
    Politics
    0.47
    Activations Density 0.000%

    No Known Activations