© 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. 71065
    Prev
    Next
    INDEX
    Explanations

    ASCII art, stories, sources

    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
    ึ้น
    0.45
    꼈
    0.43
    ্সে
    0.42
    ்க்
    0.41
    請求
    0.41
    렀
    0.41
    ses
    0.40
    定
    0.40
     Josie
    0.40
    陼
    0.39
    POSITIVE LOGITS
    atisme
    0.47
     sofr
    0.44
     mtDNA
    0.44
     fein
    0.43
     flamb
    0.42
     Fade
    0.42
     yıll
    0.42
     grasa
    0.42
     fade
    0.42
    Anaconda
    0.41
    Activations Density 0.008%

    No Known Activations