© 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. 122754
    Prev
    Next
    INDEX
    Explanations

    medical, academic, or technical terms

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

    fluctuate wildly

    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
    壬
    0.49
    漁
    0.47
    岸
    0.47
    ادو
    0.45
    ভো
    0.44
    CJK
    0.44
    副
    0.43
    若
    0.43
     Verm
    0.42
    西
    0.42
    POSITIVE LOGITS
     데이터
    0.62
     해석
    0.60
     데이터를
    0.55
     beeindruck
    0.54
     studie
    0.54
     chapitre
    0.52
     능력
    0.52
     є
    0.51
     표현
    0.51
     작
    0.50
    Activations Density 0.000%

    No Known Activations