© 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. 4702
    Prev
    Next
    INDEX
    Explanations

    code blocks and descriptions

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

    The neuron flags bits of text that read like technical or product specifications—dimensions, model numbers, units, and other hardware-style details.

    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
    ǜ
    0.79
    adinam
    0.69
    ából
    0.69
    ité
    0.67
    aktionen
    0.66
    estructura
    0.66
    ujjati
    0.64
    zovaniyu
    0.64
    alaikums
    0.64
    ómago
    0.64
    POSITIVE LOGITS
     the
    0.89
    .
    0.88
    ↵
    0.81
     $\
    0.74
    。
    0.71
     .
    0.66
    the
    0.65
     both
    0.63
             
    0.63
     a
    0.61
    Activations Density 1.145%

    No Known Activations