© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1271
    Prev
    Next
    INDEX
    Explanations

    bullet points and explanations

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

    conversational, tutorial-style explanations, especially the markers of structured outlines (section headers, colons, bullets) and contractions that signal an explanatory, step-by-step response tone.

    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_40_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
    ី
    0.17
     chaired
    0.15
     ')')
    0.15
    睑
    0.14
     zou
    0.14
     /></
    0.14
    疟
    0.14
    "),],
    0.13
     fél
    0.13
    ič
    0.13
    POSITIVE LOGITS
    စိတ်အပိုင်း
    0.14
    libraries
    0.13
     Grundlagen
    0.13
    Different
    0.13
     infographics
    0.13
    COMMON
    0.13
     ஆனால்
    0.12
     однако
    0.12
    ःख
    0.12
    emb
    0.12
    Activations Density 3.142%

    No Known Activations