© 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-262K
    7. 82350
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transition words

    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_262k_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
    ußer
    0.20
    都
    0.16
     බොහෝ
    0.16
     അവര്‍
    0.16
    抽象
    0.15
    峀
    0.15
     Schwier
    0.15
    UnderTest
    0.15
     Hau
    0.15
     Tatsache
    0.15
    POSITIVE LOGITS
    ↵
    0.19
    а
    0.18
    у
    0.17
    ан
    0.17
     vivienda
    0.17
    и
    0.16
     yaz
    0.16
    ин
    0.15
     жили
    0.15
    f
    0.15
    Activations Density 0.014%

    No Known Activations