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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 10881
    Prev
    Next
    INDEX
    Explanations

    how to start explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -2.11
     also
    -1.72
     they
    -1.65
     those
    -1.49
     their
    -1.28
     with
    -1.25
     where
    -1.23
    匾
    -1.20
     também
    -1.20
     such
    -1.20
    POSITIVE LOGITS
    めちゃくちゃ
    1.38
    総評
    1.33
    According
    1.28
    ほんと
    1.20
    関連リンク
    1.17
    凄く
    1.17
     inéd
    1.16
    ・・・・・・・・
    1.16
    3
    1.15
    When
    1.13
    Activations Density 0.015%

    No Known Activations