© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14838
    Prev
    Next
    INDEX
    Explanations

    estimate/guess

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

    The neuron strongly activates on the very first substantive word of a new section or paragraph (i.e. on the initial content-bearing token that begins a sentence or clause following a break).

    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
    ക്കാര്‍
    0.80
    谈判
    0.77
    ili
    0.76
    kih
    0.75
    3
    0.74
    aved
    0.73
    6
    0.72
    昼
    0.71
    伪
    0.70
    man
    0.69
    POSITIVE LOGITS
     LPTMR
    0.84
     ASX
    0.84
     возмо
    0.84
    ч
    0.81
     आईसीआर
    0.80
     enforceable
    0.79
    дро
    0.79
     EQS
    0.75
    тные
    0.73
    ieuses
    0.73
    Activations Density 0.000%

    No Known Activations