© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 108031
    Prev
    Next
    INDEX
    Explanations

    Scorsese movies, solutions provider

    np_acts-logits-general · gemini-2.5-flash-lite

    provider, construction, recovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     unquestionably
    0.53
    ими
    0.46
     tra
    0.46
     Paradise
    0.46
    荧
    0.45
     invariably
    0.44
     sureties
    0.44
     decidedly
    0.43
     Tra
    0.42
     overtaken
    0.42
    POSITIVE LOGITS
     నొప్పి
    0.48
     उभार
    0.48
    S
    0.48
     основы
    0.48
    Labour
    0.47
    Construct
    0.46
     खर्च
    0.46
     المشروع
    0.46
    helps
    0.46
     کمک
    0.46
    Activations Density 0.001%

    No Known Activations