© 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. 34-GEMMASCOPE-RES-131K
    4. 102933
    Prev
    Next
    INDEX
    Explanations

    quoted speech or text

    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
     not
    -1.20
     this
    -1.10
     what
    -1.03
     new
    -1.01
     While
    -1.00
     at
    -0.99
     get
    -0.98
     However
    -0.98
    While
    -0.96
     for
    -0.96
    POSITIVE LOGITS
     "
    1.20
     contiennent
    1.19
    seems
    1.18
     reprend
    1.16
     “
    1.14
     semblent
    1.12
     hunne
    1.12
    installed
    1.12
     évé
    1.10
    sonder
    1.10
    Activations Density 0.002%

    No Known Activations