© 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. 8972
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    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
     Debye
    0.58
     thermodynam
    0.56
     excreted
    0.47
    瘍
    0.46
     Faraday
    0.46
    Khokhlov
    0.46
     biliary
    0.45
    ਮੀ
    0.45
     dimensionless
    0.44
     amide
    0.44
    POSITIVE LOGITS
    Early
    0.57
     Early
    0.51
    Subtract
    0.46
    KeyboardView
    0.46
    빠
    0.46
    Addition
    0.45
    Shopping
    0.45
     गिनती
    0.45
    Calendar
    0.44
    Mental
    0.44
    Activations Density 0.244%

    No Known Activations