© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13327
    Prev
    Next
    INDEX
    Explanations

    list slicing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    दारा
    3.13
    ﺪ
    2.98
    𝘶
    2.96
    Թ
    2.93
    šću
    2.89
    Ｆ
    2.89
    ᾧ
    2.88
     barg
    2.87
     lưới
    2.87
     ƯCLN
    2.82
    POSITIVE LOGITS
    ی
    3.28
    ATION
    2.81
    ding
    2.76
    ation
    2.76
    man
    2.70
     Scripts
    2.66
    pana
    2.65
    dle
    2.62
    ma
    2.61
    lers
    2.56
    Activations Density 0.002%

    No Known Activations