© 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. 31-GEMMASCOPE-2-RES-262K
    7. 76398
    Prev
    Next
    INDEX
    Explanations

    business and technical domains

    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_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
     хво
    0.54
     ჟ
    0.48
     compromise
    0.47
     М
    0.46
     स्वरों
    0.46
    ርስ
    0.45
     КО
    0.45
    getZoom
    0.44
     ஸ்ப
    0.44
    រយៈ
    0.44
    POSITIVE LOGITS
    sche
    0.47
    i
    0.46
     sekaligus
    0.45
    いを
    0.44
     across
    0.44
     fired
    0.44
     followed
    0.43
     swept
    0.43
     dabei
    0.42
    生死
    0.42
    Activations Density 0.001%

    No Known Activations