© 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. 1583
    Prev
    Next
    INDEX
    Explanations

    still

    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
    次に
    0.92
     BAD
    0.87
     겁니다
    0.84
    \|=\
    0.82
    と思った
    0.81
    qualiter
    0.77
    })=\
    0.77
    oses
    0.77
    ________
    0.76
    hipi
    0.76
    POSITIVE LOGITS
     still
    5.14
     STILL
    4.63
    still
    4.58
    Still
    4.52
     Still
    4.44
     masih
    4.20
     ancora
    4.11
     ainda
    4.06
     fortfarande
    4.04
    仍
    4.04
    Activations Density 2.291%

    No Known Activations