© 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. 12-GEMMASCOPE-2-RES-16K
    7. 12
    Prev
    Next
    INDEX
    Explanations

    ' followed by 't' or 'm'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
     somit
    0.62
     dichotom
    0.59
    Я
    0.57
     быть
    0.55
     MNRAS
    0.54
     unsure
    0.53
    न
    0.52
     ilość
    0.51
     elucid
    0.51
    本质
    0.51
    POSITIVE LOGITS
    َ
    0.60
    Defender
    0.51
    ut
    0.49
    PMorgan
    0.47
    响起
    0.47
     rechaz
    0.47
    :‏
    0.47
    af
    0.46
     지난해
    0.46
    。
    0.46
    Activations Density 4.637%

    No Known Activations