© 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. 103411
    Prev
    Next
    INDEX
    Explanations

    Names starting with Jon or Jonath

    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
    形状
    -0.84
     dedicato
    -0.84
     tasca
    -0.83
     messa
    -0.82
     Munic
    -0.80
    ities
    -0.78
     Saloon
    -0.78
     Sinf
    -0.78
     dess
    -0.78
     codice
    -0.76
    POSITIVE LOGITS
    Jon
    1.30
    athon
    1.27
     Jon
    1.22
    ATHAN
    1.08
     jon
    0.96
    Jonathan
    0.94
    than
    0.92
    JON
    0.86
    quille
    0.84
    جون
    0.83
    Activations Density 0.009%

    No Known Activations