© 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. 40-GEMMASCOPE-2-RES-262K
    7. 29457
    Prev
    Next
    INDEX
    Explanations

    stairway to heaven

    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_40_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
    Unified
    0.40
    рель
    0.40
    unified
    0.38
     StreamReader
    0.38
    class
    0.38
    魎
    0.37
    rawberry
    0.36
    trial
    0.36
    Servers
    0.36
    Becoming
    0.36
    POSITIVE LOGITS
    nial
    0.54
     atend
    0.42
    tes
    0.41
    𝗇
    0.39
    টর
    0.38
    те
    0.37
     oxidize
    0.37
     atender
    0.37
     те
    0.37
     जाएं
    0.37
    Activations Density 0.003%

    No Known Activations