© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9676
    Prev
    Next
    INDEX
    Explanations

    as far back as

    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_13_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
    めっちゃ
    1.68
     fucked
    1.53
     shit
    1.53
     shitty
    1.50
     merda
    1.28
     ✅
    1.24
    eeee
    1.23
     bahut
    1.21
    诶
    1.17
     fucking
    1.16
    POSITIVE LOGITS
    retirement
    1.40
     retirement
    1.34
     demonstrating
    1.32
     regulating
    1.31
     sophistication
    1.30
    ByURL
    1.29
     Retirement
    1.29
     quoting
    1.26
     Kerry
    1.26
     journalism
    1.26
    Activations Density 0.104%

    No Known Activations