© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1461
    Prev
    Next
    INDEX
    Explanations

    make sure

    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_17_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
    precise
    0.98
    )['
    0.94
     credible
    0.94
     प्राथमिकी
    0.93
    aqueous
    0.93
    scalable
    0.91
    worst
    0.89
    viable
    0.89
    },(
    0.88
    >≥</
    0.87
    POSITIVE LOGITS
     decided
    1.43
    来到了
    1.37
     oldukça
    1.29
    ちょっと
    1.29
     muito
    1.27
     interestingly
    1.26
    为大家
    1.25
     alot
    1.24
    ということで
    1.24
     opět
    1.23
    Activations Density 0.886%

    No Known Activations