© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9116
    Prev
    Next
    INDEX
    Explanations

    fraction of a half

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

    the presence of floating‐point numerical literals (numbers with decimal points) in the 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_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
     (−
    0.63
     ១
    0.57
    =((
    0.54
     ((
    0.53
     थ्री
    0.53
     Monkeys
    0.53
     Slightly
    0.53
     Suppression
    0.53
    োন
    0.52
     (-
    0.52
    POSITIVE LOGITS
    不可
    0.57
     proprio
    0.56
     tegas
    0.54
    位於
    0.52
     comune
    0.51
    潔
    0.51
    ∈</
    0.50
     mumkin
    0.50
     रुच
    0.50
    やすい
    0.49
    Activations Density 0.032%

    No Known Activations