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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73311
    Prev
    Next
    INDEX
    Explanations

    categories or specific contexts

    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
     our
    -1.67
     السياس
    -1.58
     commence
    -1.27
     Wiking
    -1.24
     $
    -1.18
     must
    -1.17
    jScrollPane
    -1.13
     rezept
    -1.11
     we
    -1.11
     then
    -1.10
    POSITIVE LOGITS
    簡單
    1.21
    Kleur
    1.19
    Akhir
    1.19
     प्रोड
    1.17
     景色
    1.13
     наконец
    1.13
     स्क्रीन
    1.12
     comté
    1.11
    Цитата
    1.10
    மான
    1.10
    Activations Density 0.000%

    No Known Activations