© 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. 19101
    Prev
    Next
    INDEX
    Explanations

    numbered list items

    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
     even
    -1.54
    0
    -1.48
    \
    -1.47
    ".
    -1.38
     for
    -1.36
    2
    -1.31
     but
    -1.31
    教你
    -1.30
    but
    -1.26
     its
    -1.20
    POSITIVE LOGITS
    戗
    1.54
    alties
    1.45
    mability
    1.45
    葙
    1.43
     observa
    1.41
     abitanti
    1.40
     atitude
    1.39
    ·
    1.39
    芻
    1.36
     dichi
    1.35
    Activations Density 0.114%

    No Known Activations