© 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. 159769
    Prev
    Next
    INDEX
    Explanations

    Dead Sea location and composition

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

    increase engagement, product, more other

    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
    იც
    0.47
    到
    0.47
    不會
    0.46
    不会
    0.46
     দুর্নীতি
    0.46
    etli
    0.46
    こちらも
    0.46
     "["
    0.46
    国の
    0.45
     बचाता
    0.44
    POSITIVE LOGITS
    ize
    0.46
     township
    0.41
     أص
    0.40
     прият
    0.38
     Malang
    0.38
    ichar
    0.38
    ther
    0.37
     passenger
    0.37
     centrale
    0.37
     gmin
    0.37
    Activations Density 0.002%

    No Known Activations