© 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. 11109
    Prev
    Next
    INDEX
    Explanations

    policy, species, institutions

    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
     argue
    0.48
     is
    0.46
    a
    0.46
    rhein
    0.45
     spok
    0.45
     though
    0.44
     originally
    0.44
     argued
    0.44
     has
    0.44
    top
    0.44
    POSITIVE LOGITS
     universidad
    0.54
     enferm
    0.49
    ೀಲ
    0.48
    𒌅
    0.48
     exercícios
    0.46
     افزایش
    0.46
    ሎች
    0.46
     enfermedades
    0.46
     heridas
    0.46
    ፊ
    0.45
    Activations Density 0.037%

    No Known Activations