© 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. 84336
    Prev
    Next
    INDEX
    Explanations

    Republic

    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
     \
    -1.18
    N
    -1.15
     didn
    -1.13
    -1.13
     __
    -1.13
     again
    -1.11
     I
    -1.09
    L
    -1.09
     L
    -1.09
     (!__
    -1.09
    POSITIVE LOGITS
    がありますが
    1.28
    سياسي
    1.24
    見到
    1.23
     joyeux
    1.20
    ディスプレイ
    1.13
    声が
    1.13
     laku
    1.13
     maksi
    1.13
    🎦
    1.12
    UCIÓN
    1.11
    Activations Density 0.398%
    No Known Activations