© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56143
    Prev
    Next
    INDEX
    Explanations

    months and bounds

    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
    Negative Logits
    SPs
    0.41
     Mili
    0.41
    
    0.40
    posterous
    0.40
     타이
    0.39
    军事
    0.39
     про
    0.39
     அல்லது
    0.38
     နဲ့
    0.38
    癃
    0.38
    POSITIVE LOGITS
    Fall
    0.41
     bittersweet
    0.41
     setia
    0.39
    Grazie
    0.38
    etsa
    0.38
    colors
    0.37
     antaranya
    0.37
    iana
    0.37
     id
    0.37
    etti
    0.37
    Activations Density 0.001%

    No Known Activations