© 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. 62634
    Prev
    Next
    INDEX
    Explanations

    foreign words for if and you

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

    parenthetical phrases and conjunctions

    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
    el
    0.45
    ados
    0.44
     Bertram
    0.43
    λο
    0.43
    公元
    0.43
    ≾
    0.43
    來越
    0.42
    述べ
    0.42
     зимо
    0.42
     કર્મ
    0.42
    POSITIVE LOGITS
    אם
    0.54
     bạn
    0.47
     Bạn
    0.47
     nếu
    0.47
     jika
    0.47
     möglicherweise
    0.46
     dacă
    0.46
     nuovi
    0.45
     inflatable
    0.44
     אתה
    0.44
    Activations Density 0.000%

    No Known Activations