© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2576
    Prev
    Next
    INDEX
    Explanations

    code now includes

    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_16k_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
    .`);
    0.33
    特に
    0.33
     Thankfully
    0.32
     İş
    0.32
     تمامی
    0.32
    )–
    0.31
    
    0.31
     காரணமாக
    0.30
    ₁.
    0.30
    .–
    0.30
    POSITIVE LOGITS
    ACION
    0.35
     kunj
    0.35
    ник
    0.35
    neurs
    0.33
     okam
    0.33
     heeft
    0.32
     enk
    0.32
     arro
    0.32
     fraternity
    0.32
     onOptions
    0.32
    Activations Density 0.113%

    No Known Activations