© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28564
    Prev
    Next
    INDEX
    Explanations

    errors, exceptions, unexpected

    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
     apporter
    -1.08
     refroid
    -1.05
     zerst
    -1.05
     occuper
    -1.04
     ajedrez
    -0.99
     poë
    -0.99
     poucos
    -0.98
     horloge
    -0.96
     faciliter
    -0.96
     feront
    -0.96
    POSITIVE LOGITS
     this
    1.59
     their
    1.41
     during
    1.34
     all
    1.34
     strange
    1.17
     never
    1.14
     unexpected
    1.13
     because
    1.09
     saw
    1.09
     after
    1.08
    Activations Density 0.008%

    No Known Activations