© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 506
    Prev
    Next
    INDEX
    Explanations

    firstly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    也會
    0.46
    也会
    0.40
     ALSO
    0.29
    ↵↵
    0.29
     också
    0.28
    也能
    0.28
    ↵↵↵↵↵
    0.28
     таксама
    0.27
    也要
    0.27
    也在
    0.27
    POSITIVE LOGITS
     Öncelikle
    0.44
     Firstly
    0.33
     firstly
    0.30
     প্রথমেই
    0.29
     Although
    0.29
     A
    0.29
     Despite
    0.29
    Firstly
    0.29
     The
    0.28
     Несмотря
    0.28
    Activations Density 0.604%

    No Known Activations