© 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. 14864
    Prev
    Next
    INDEX
    Explanations

    Bollinger Bands, Lucid Sex, Beautiful Soup, JeffDeque

    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
     cancelButton
    2.26
    КИ
    2.23
     క
    2.06
     下さい
    2.04
    ytically
    2.03
     いたし
    2.00
     macroscopic
    1.98
    FindingsRequest
    1.95
     符合
    1.94
    жения
    1.94
    POSITIVE LOGITS
    u
    1.67
     Or
    1.56
    us
    1.55
    Or
    1.46
    a
    1.44
    r
    1.36
    ada
    1.33
    um
    1.32
    n
    1.30
    ut
    1.30
    Activations Density 0.097%

    No Known Activations