© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 5782
    Prev
    Next
    INDEX
    Explanations

    Selected Ambient Works

    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_all/layer_41_width_262k_l0_big
    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
     unpack
    0.43
     onshore
    0.41
     loot
    0.41
     ICO
    0.41
     మొక్క
    0.40
     didn
    0.39
    伒
    0.39
     artificially
    0.38
     refurbishment
    0.38
    绘制
    0.38
    POSITIVE LOGITS
    hears
    0.46
    img
    0.43
    awy
    0.43
    auschen
    0.43
    āda
    0.41
    ἀ
    0.41
    जिन
    0.40
    گاهی
    0.40
    opia
    0.40
     désir
    0.40
    Activations Density 7.351%

    No Known Activations