© 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. 10-GEMMASCOPE-RES-131K
    4. 61363
    Prev
    Next
    INDEX
    Explanations

    important outcomes and decisions

    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
     that
    -1.56
     Erlebn
    -1.55
     only
    -1.43
     Any
    -1.41
     advirtió
    -1.41
     município
    -1.37
     of
    -1.35
     always
    -1.34
    iscono
    -1.34
     There
    -1.32
    POSITIVE LOGITS
    gencias
    1.45
     into
    1.39
     assorted
    1.33
     現貨
    1.32
     včetně
    1.30
    َه
    1.27
     отличается
    1.24
     zey
    1.22
     guardi
    1.20
     แต่
    1.20
    Activations Density 0.036%

    No Known Activations