© 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. 34-GEMMASCOPE-RES-131K
    7. 60245
    Prev
    Next
    INDEX
    Explanations

    available or availability

    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_34/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
     wither
    -1.40
    1
    -1.39
     vastly
    -1.27
    妧
    -1.26
     bezw
    -1.23
     getragen
    -1.23
     cercare
    -1.20
     chinh
    -1.19
     așa
    -1.19
     început
    -1.19
    POSITIVE LOGITS
     for
    2.05
     to
    2.00
     This
    1.64
     What
    1.41
     from
    1.41
     at
    1.39
     information
    1.38
     in
    1.37
     Surprisingly
    1.36
     Some
    1.35
    Activations Density 0.037%

    No Known Activations