© 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. 217963
    Prev
    Next
    INDEX
    Explanations

    DJ protection password

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

    ZuluPunk Scavenge Directions

    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
     siècles
    0.51
     tomó
    0.50
     takiej
    0.50
    éis
    0.47
     happens
    0.47
    =='
    0.47
     occurs
    0.46
     être
    0.46
    ),
    0.45
     happen
    0.45
    POSITIVE LOGITS
    zona
    0.42
    י
    0.40
     Kenney
    0.39
    Zona
    0.38
    sylvania
    0.37
    Responses
    0.37
     அப்படியே
    0.37
    യാ
    0.36
    出来的
    0.36
     Shirley
    0.36
    Activations Density 0.001%

    No Known Activations