© 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. 1191
    Prev
    Next
    INDEX
    Explanations

    depends on specifics

    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
    ו
    2.64
    षु
    2.56
    le
    2.22
    험
    2.18
    中标
    2.18
    வெளி
    2.18
    lecht
    2.12
    erson
    2.04
    꾿
    2.01
     অন
    2.01
    POSITIVE LOGITS
    𝒅
    2.83
    তাবাদী
    2.74
    iteit
    2.72
    ómica
    2.63
    掍
    2.63
    arán
    2.58
    lify
    2.57
    izations
    2.56
    𝚂
    2.50
    𝑻
    2.48
    Activations Density 0.231%

    No Known Activations