© 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. 34684
    Prev
    Next
    INDEX
    Explanations

    technical compilation, ML, and devices

    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
    ת
    0.54
    ْر
    0.49
    Թ
    0.48
    או
    0.47
    /{
    0.43
    uhà
    0.43
    א
    0.42
    Զ
    0.42
    -}$
    0.42
    ̹
    0.41
    POSITIVE LOGITS
     institutions
    0.52
     Sundays
    0.45
     schools
    0.43
     exponential
    0.42
     Optimization
    0.42
     optimizes
    0.41
     referrals
    0.41
     holidays
    0.41
     Austin
    0.41
     something
    0.40
    Activations Density 0.004%

    No Known Activations