© 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. 9599
    Prev
    Next
    INDEX
    Explanations

    from past experience

    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
     was
    -1.45
    dddd
    -1.34
    monger
    -1.31
     cuando
    -1.30
    OOOO
    -1.27
    OOOOOO
    -1.27
    OOOOO
    -1.27
    regarding
    -1.24
     ugyan
    -1.22
     déjà
    -1.19
    POSITIVE LOGITS
     which
    1.63
    hline
    1.62
    ucleotide
    1.50
    櫚
    1.48
    architecte
    1.43
     know
    1.42
     glauben
    1.36
    écrivain
    1.36
     présidentielle
    1.35
     zimní
    1.35
    Activations Density 0.061%

    No Known Activations