© 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. 13638
    Prev
    Next
    INDEX
    Explanations

    typename T templates

    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
    ्रेट
    3.15
    пы
    3.01
    пыт
    2.87
    𝗸
    2.84
     होप
    2.78
    ంచెం
    2.77
    Ḫ
    2.73
    anic
    2.68
    sts
    2.66
    輯
    2.65
    POSITIVE LOGITS
    em
    2.28
    t
    2.25
    ismer
    2.12
    ens
    2.11
    ーション
    2.09
    ्य
    2.07
     _$
    1.97
    ع
    1.96
    köz
    1.94
    itamins
    1.92
    Activations Density 0.010%

    No Known Activations