© 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. 28533
    Prev
    Next
    INDEX
    Explanations

    times and time zones

    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
     signified
    0.42
    austral
    0.39
    allele
    0.38
    Ellipse
    0.38
    웜
    0.38
    JAVADOC
    0.37
    debian
    0.37
     বঙ্গ
    0.36
    াং
    0.36
     prolet
    0.36
    POSITIVE LOGITS
     unor
    0.41
     funct
    0.39
    貌
    0.39
     Frankfurt
    0.38
     Fintech
    0.38
     locally
    0.38
     Δ
    0.38
    गिरी
    0.37
     binders
    0.37
    participant
    0.37
    Activations Density 0.007%

    No Known Activations