© 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. 204334
    Prev
    Next
    INDEX
    Explanations

    SCSS styling and imports

    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
    ᒥ
    0.43
    ನ್
    0.43
    razione
    0.42
     လက်
    0.41
    unus
    0.41
    Metaxy
    0.40
    𝙃
    0.39
    ուն
    0.38
    θυν
    0.38
     తిరిగి
    0.38
    POSITIVE LOGITS
    gau
    0.43
    آور
    0.39
     Presidential
    0.39
     employee
    0.38
     city
    0.38
     covenant
    0.37
    
    0.37
     modular
    0.37
     gus
    0.37
     MAS
    0.36
    Activations Density 0.001%

    No Known Activations