© 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. 48196
    Prev
    Next
    INDEX
    Explanations

    not

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

    mentions of code snippets, especially Markdown-style inline code and fenced code blocks.

    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
     Jeff
    0.38
     Est
    0.38
    icar
    0.37
     sanitaire
    0.36
     Mark
    0.36
     esters
    0.36
     X
    0.35
     Geographical
    0.35
     Prospects
    0.34
     É
    0.33
    POSITIVE LOGITS
    のではなく
    0.70
    ではなく
    0.67
     instead
    0.62
    Instead
    0.62
     नही
    0.57
    而不是
    0.56
     نہيں
    0.53
     হবেনা
    0.53
     değil
    0.52
    instead
    0.52
    Activations Density 0.189%

    No Known Activations