© 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. 530
    Prev
    Next
    INDEX
    Explanations

    the `name`, `color`, `method`, `size`, `Ather`

    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
    g
    1.02
    s
    0.98
    mselves
    0.94
    ll
    0.82
    d
    0.80
    h
    0.77
    x
    0.74
    ne
    0.73
    deki
    0.71
     द
    0.69
    POSITIVE LOGITS
    ৮
    0.77
    俚
    0.76
    ش
    0.75
    ਜ਼
    0.73
    िंग
    0.71
    ИС
    0.70
    ერ
    0.68
    та
    0.68
    ड़ियां
    0.68
     作詞
    0.68
    Activations Density 0.536%

    No Known Activations