© 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. 110899
    Prev
    Next
    INDEX
    Explanations

    code and programming terms

    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
    𝘭
    0.55
    arod
    0.52
    कांची
    0.51
     इनटू
    0.50
    omus
    0.49
    PLL
    0.49
    चलर्स
    0.48
     october
    0.48
    絓
    0.48
    برای
    0.47
    POSITIVE LOGITS
    0.45
     sogen
    0.39
     Martín
    0.38
     Hash
    0.38
     Tengo
    0.37
     Änderungen
    0.37
     Condiciones
    0.37
     Hillsborough
    0.37
     hash
    0.36
     Mehr
    0.36
    Activations Density 0.001%

    No Known Activations