© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 3438
    Prev
    Next
    INDEX
    Explanations

    on surfaces

    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
     निहित
    0.44
    ວນ
    0.44
     وہی
    0.43
     במס
    0.42
    䐍
    0.42
     حسین
    0.41
     cuarta
    0.41
     なかっ
    0.41
     माइट
    0.41
     समिती
    0.41
    POSITIVE LOGITS
     surfaces
    0.59
     surface
    0.52
     shelf
    0.47
    ↵↵
    0.47
    merksam
    0.46
     superficies
    0.46
     personnes
    0.46
     napkin
    0.44
     comedian
    0.44
     lists
    0.44
    Activations Density 0.133%

    No Known Activations