© 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-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 841
    Prev
    Next
    INDEX
    Explanations

    just like a

    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
    屓
    3.00
    舝
    2.99
     całość
    2.82
    हेब
    2.76
     Gli
    2.74
    archiwizowane
    2.71
    поряд
    2.61
    িন্ত
    2.56
    çok
    2.55
    денти
    2.50
    POSITIVE LOGITS
    br
    2.76
    a
    2.36
     br
    2.17
    ა
    2.14
    া
    2.12
    ্ম্ম
    2.09
    ism
    2.07
     historic
    2.06
    ﯽ
    2.05
     limit
    2.05
    Activations Density 0.176%

    No Known Activations