© 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. 4425
    Prev
    Next
    INDEX
    Explanations

    explaining or giving examples

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

    requests and content related to programming/code (including code blocks and technical prompts), often spiking around conversation turn-boundary tokens.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     ওই
    0.44
     apparently
    0.38
    apparently
    0.36
    OffsetY
    0.35
     vendar
    0.35
     miatt
    0.33
     arginine
    0.33
    RefreshToken
    0.33
    회가
    0.32
     নাকি
    0.32
    POSITIVE LOGITS
     பொதுவாக
    0.52
     สำหรับ
    0.51
     সাধারণত
    0.49
    สำหรับ
    0.47
     Examples
    0.46
    Для
    0.45
     다양한
    0.43
     Typically
    0.43
     Descripción
    0.43
     Beispiele
    0.42
    Activations Density 0.406%

    No Known Activations