© 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. 2214
    Prev
    Next
    INDEX
    Explanations

    length or size of collections

    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
     with
    -1.33
     would
    -1.14
     for
    -1.13
     at
    -1.11
     over
    -1.08
     what
    -1.06
     is
    -1.06
     as
    -0.96
     or
    -0.96
     only
    -0.95
    POSITIVE LOGITS
     length
    1.70
    length
    1.50
     size
    1.30
     Tamanho
    1.24
    
    1.20
    Length
    1.20
     duration
    1.20
    GetLength
    1.14
     Infór
    1.11
     LENGTH
    1.10
    Activations Density 0.005%

    No Known Activations