© 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. 25774
    Prev
    Next
    INDEX
    Explanations

    domain availability search

    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
     энцикло
    0.46
    Unhandled
    0.46
    CLOUD
    0.43
    Lot
    0.42
    Pr
    0.42
    File
    0.41
     Свет
    0.41
    Х
    0.41
    Marks
    0.40
    теше
    0.40
    POSITIVE LOGITS
    जुर्ग
    0.49
     patent
    0.48
     വൈദ്യുതി
    0.47
    ídu
    0.46
    美国
    0.45
     featuring
    0.45
     suoi
    0.45
     ayant
    0.44
     noen
    0.44
     nitidus
    0.44
    Activations Density 0.002%

    No Known Activations