© 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. 50484
    Prev
    Next
    INDEX
    Explanations

    initiating clauses or continuing thoughts

    np_acts-logits-general · gemini-2.5-flash-lite

    urgent and important

    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
     that
    0.54
     scout
    0.49
     the
    0.48
     Samantha
    0.48
     F
    0.48
     specific
    0.47
     SB
    0.47
     कुंडली
    0.47
     riots
    0.47
     their
    0.47
    POSITIVE LOGITS
    ᓪ
    0.51
    oxygène
    0.50
    نا
    0.48
    억원
    0.48
    ه‌ای
    0.47
    دە
    0.47
    ầm
    0.47
    <unused4>
    0.46
    اداسی
    0.46
    辂
    0.46
    Activations Density 0.000%

    No Known Activations