© 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. 98193
    Prev
    Next
    INDEX
    Explanations

    community, we, our

    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
    Ṛ
    -1.34
    האם
    -1.25
    ဧ
    -1.23
     berkomunikasi
    -1.22
    勠
    -1.20
    Hilsen
    -1.18
    schon
    -1.16
    dateien
    -1.13
     saine
    -1.12
     escritor
    -1.11
    POSITIVE LOGITS
     we
    1.72
     our
    1.59
     today
    1.27
     tutaj
    1.20
     trabaja
    1.19
    是我们
    1.19
     actually
    1.17
     residents
    1.16
    ですので
    1.15
     they
    1.14
    Activations Density 0.016%

    No Known Activations