© 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. 135693
    Prev
    Next
    INDEX
    Explanations

    non-english 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
     samband
    0.43
    警
    0.40
     grantor
    0.39
    时长
    0.39
     headcount
    0.39
     आपको
    0.38
     CFI
    0.38
     fundraising
    0.38
    County
    0.38
     बदलकर
    0.37
    POSITIVE LOGITS
    iteurs
    0.47
    ת
    0.45
    統合
    0.44
    öss
    0.44
     경쟁
    0.43
    ös
    0.43
     ਹਨ
    0.43
    입
    0.42
    เต็ม
    0.42
    ING
    0.42
    Activations Density 0.009%

    No Known Activations