© 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. 34-GEMMASCOPE-RES-131K
    7. 102960
    Prev
    Next
    INDEX
    Explanations

    announcements and software files

    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_34/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
    ̭
    -0.79
    OptionsMenu
    -0.78
     whatever
    -0.77
    rui
    -0.77
    leftrightarrow
    -0.76
     Knapp
    -0.76
    iduous
    -0.76
    assion
    -0.75
    itate
    -0.75
    itized
    -0.75
    POSITIVE LOGITS
     partnerships
    0.96
     announce
    0.94
     announcing
    0.85
    お知らせ
    0.84
    Other
    0.82
    📘
    0.82
     announced
    0.81
     announcement
    0.79
     announces
    0.79
     other
    0.77
    Activations Density 0.013%

    No Known Activations