© 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. 161342
    Prev
    Next
    INDEX
    Explanations

    adverb or pronoun + word

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

    non-english or specialized

    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
    ه
    0.54
    ра
    0.49
    ва
    0.47
    ي
    0.43
    参加
    0.43
    ون
    0.42
    تر
    0.42
    ві
    0.42
     Knesset
    0.42
    ROUND
    0.42
    POSITIVE LOGITS
     orgánica
    0.47
     λεπ
    0.46
     содержания
    0.45
     italics
    0.45
     chloroform
    0.44
     نموذج
    0.43
     unserem
    0.43
     glPushMatrix
    0.43
     সেগুলি
    0.43
    এটি
    0.42
    Activations Density 0.000%

    No Known Activations