© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114053
    Prev
    Next
    INDEX
    Explanations

    cross-platform software

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

    references to cross-platform or multi-platform software development and compatibility.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     』
    -1.60
    )]
    -1.45
    }}}{\
    -1.42
    〖
    -1.37
    亙
    -1.35
    をしていた
    -1.31
     "
    -1.30
     sebagai
    -1.29
    !
    -1.27
    اخته
    -1.26
    POSITIVE LOGITS
    3
    1.62
    2
    1.51
    4
    1.45
     like
    1.43
    6
    1.39
    b
    1.38
    d
    1.38
    p
    1.38
    w
    1.27
     -
    1.26
    Activations Density 0.064%

    No Known Activations