© 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. 19004
    Prev
    Next
    INDEX
    Explanations

    legal, logging, or water

    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
     działa
    0.49
     నేను
    0.48
    тельной
    0.47
     தற்போது
    0.47
     සිදු
    0.46
     छत्तीस
    0.46
     traumat
    0.46
    懟
    0.46
     நடந்து
    0.45
    🐰
    0.45
    POSITIVE LOGITS
     certain
    0.48
     shorth
    0.44
     even
    0.44
    ክ
    0.43
     destinations
    0.41
     equivalents
    0.40
    s
    0.40
     routes
    0.39
     packages
    0.39
     or
    0.39
    Activations Density 0.007%

    No Known Activations