© 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. 114515
    Prev
    Next
    INDEX
    Explanations

    counterparts, agreement, seasonally, troops

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

    current conversation context

    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
    やっと
    0.51
    澪
    0.50
     ?",
    0.50
    वेंट
    0.50
     permanece
    0.49
     permanec
    0.48
     adquirir
    0.48
    ಡಿದ
    0.48
    বত
    0.47
     adqu
    0.47
    POSITIVE LOGITS
    న్‌
    0.54
    ضاء
    0.48
    ◌
    0.46
     Camp
    0.44
    situ
    0.43
     LAW
    0.43
    لاه
    0.41
     Squ
    0.41
    ؍
    0.41
     sytuacji
    0.39
    Activations Density 0.000%

    No Known Activations