© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43167
    Prev
    Next
    INDEX
    Explanations

    galaxies and paleo groups

    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
    zeme
    0.48
    ි
    0.44
    торой
    0.44
    nesto
    0.43
    icions
    0.42
    ၶ
    0.42
    鋆
    0.42
    搆
    0.41
    तेला
    0.40
    ين
    0.39
    POSITIVE LOGITS
     bathed
    0.44
     acoust
    0.43
     acúst
    0.42
     Hals
    0.42
     gorge
    0.41
     acoustic
    0.40
     bathrooms
    0.39
     network
    0.39
     नॉ
    0.39
     duż
    0.38
    Activations Density 0.002%

    No Known Activations