© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 76996
    Prev
    Next
    INDEX
    Explanations

    startups sponsorships accelerators metrics

    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
    erian
    0.44
    átku
    0.41
    त
    0.41
    onu
    0.41
     vá
    0.40
    arang
    0.40
    、
    0.40
    álne
    0.40
    궈
    0.40
    xcuserdatad
    0.39
    POSITIVE LOGITS
     Sponsorship
    0.52
     startups
    0.46
     Acceleration
    0.46
     accelerator
    0.45
     Startup
    0.45
     Από
    0.44
     Phát
    0.44
    5
    0.44
     Replacement
    0.44
     beber
    0.43
    Activations Density 0.002%

    No Known Activations