© 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. 40-GEMMASCOPE-2-RES-262K
    7. 168216
    Prev
    Next
    INDEX
    Explanations

    Godot signals

    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_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
     citizen
    0.42
     ciudadano
    0.41
     societal
    0.41
     appunto
    0.38
    ሮችን
    0.38
     창
    0.37
     forl
    0.37
     ቀለም
    0.37
     tiap
    0.37
     sponsor
    0.37
    POSITIVE LOGITS
    Downloads
    0.46
     ডাউনলোড
    0.45
    downloader
    0.45
     دانلود
    0.45
    downloads
    0.44
    دانلود
    0.41
    file
    0.41
    Latitude
    0.41
    ダウンロード
    0.40
    📧
    0.39
    Activations Density 0.008%

    No Known Activations