© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31975
    Prev
    Next
    INDEX
    Explanations

    Lloyds Register, inroads

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

    collapse, collapse, fostering

    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
    Not in Any Lists

    No Comments

    Negative Logits
     in
    0.60
     Gab
    0.50
    1
    0.50
     Berlin
    0.47
     rö
    0.47
     painted
    0.46
     go
    0.46
     don
    0.46
     no
    0.45
     ­
    0.45
    POSITIVE LOGITS
    ਾਕ
    0.62
    襷
    0.57
    
    0.56
    ﻥ
    0.54
    recommended
    0.54
    𝜁
    0.52
    管理者
    0.51
    ᱕
    0.51
    সকল
    0.50
    ཋ
    0.50
    Activations Density 0.000%

    No Known Activations