© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46473
    Prev
    Next
    INDEX
    Explanations

    linguistic constituents, grammar, intonation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pemasaran
    0.48
     ताकि
    0.45
     działania
    0.44
    的管理
    0.43
    ത്തിലേക്ക്
    0.42
     Aujourd
    0.41
    شارك
    0.40
    <unused283>
    0.40
    <unused197>
    0.39
    沢山
    0.39
    POSITIVE LOGITS
    ၞ
    0.49
     বুঝিতে
    0.46
    ンの
    0.46
     syllable
    0.43
    inton
    0.43
     Linguistic
    0.42
    oubt
    0.41
     বলিলেন
    0.41
     व्याकरण
    0.41
     constituents
    0.40
    Activations Density 0.019%

    No Known Activations