© 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. 10-GEMMASCOPE-RES-131K
    7. 12293
    Prev
    Next
    INDEX
    Explanations

    go for it

    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_10/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
    =“
    -1.46
    ($)
    -1.37
     dotyczące
    -1.35
     here
    -1.33
     comprehensively
    -1.32
    ,\\
    -1.30
     such
    -1.28
    킵
    -1.26
     cocinas
    -1.26
    鈇
    -1.25
    POSITIVE LOGITS
    owulf
    1.47
     únicamente
    1.41
     same
    1.34
     was
    1.32
    Subgoals
    1.31
    ranslated
    1.30
    lusconi
    1.30
     dialami
    1.28
     邊
    1.26
    那边
    1.24
    Activations Density 0.023%

    No Known Activations