© 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. 28235
    Prev
    Next
    INDEX
    Explanations

    . followed by words

    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
     seemed
    -1.41
     seems
    -1.32
    感觉
    -1.20
     вроде
    -1.17
     vraiment
    -1.09
     semble
    -1.09
    なんですが
    -1.07
    忏
    -1.05
     seem
    -1.05
     really
    -1.04
    POSITIVE LOGITS
     you
    1.41
     никакого
    1.20
     ucap
    1.17
    adə
    1.17
     даже
    1.16
     countless
    1.16
     beina
    1.13
    ֊
    1.12
     justement
    1.09
     voient
    1.09
    Activations Density 0.056%

    No Known Activations