© 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-262K
    7. 83523
    Prev
    Next
    INDEX
    Explanations

    color palette

    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
    installment
    0.47
    唝
    0.47
     rejoicing
    0.45
    ರಿನ
    0.45
    ানোর
    0.44
    परेटर
    0.44
    อย่าง
    0.43
    bringing
    0.43
    ירות
    0.42
    น้อย
    0.42
    POSITIVE LOGITS
    l
    0.54
    s
    0.51
     gacche
    0.48
     y
    0.47
    y
    0.47
    v
    0.46
     eczema
    0.44
    oglobin
    0.43
     Urlaub
    0.43
    enance
    0.42
    Activations Density 0.003%

    No Known Activations