© 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
    2. Gemma-3-12B
    3. 12-GEMMASCOPE-2-RES-16K
    4. 67
    Prev
    Next
    INDEX
    Explanations

    WeChat call

    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
    שת
    0.95
    了一个
    0.94
    ores
    0.91
    彡
    0.87
    לא
    0.83
    คือ
    0.83
    기업
    0.83
    pués
    0.82
    ujjati
    0.81
    ית
    0.80
    POSITIVE LOGITS
    theless
    1.21
    shire
    1.13
    ли
    1.12
    referred
    1.07
    an
    1.05
    s
    1.05
    the
    1.00
    trombone
    0.98
     Aidan
    0.98
    am
    0.97
    Activations Density 3.214%

    No Known Activations