© 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. 85202
    Prev
    Next
    INDEX
    Explanations

    parts of machines, hormones, or abilities

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

    language and instructions

    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
    2
    0.54
     Griff
    0.51
     Easton
    0.47
     Edmond
    0.46
     Tipp
    0.46
     Decatur
    0.46
     Hals
    0.45
     etab
    0.44
     Thema
    0.44
     Garner
    0.43
    POSITIVE LOGITS
     megawatts
    0.52
     ပါ
    0.51
     kilograms
    0.50
     personas
    0.49
     失
    0.49
     toughness
    0.48
     ဂ
    0.48
    languages
    0.47
     သ
    0.47
    ാപാ
    0.47
    Activations Density 0.000%

    No Known Activations