© 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. 90956
    Prev
    Next
    INDEX
    Explanations

    sentence starters

    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
    -0.93
     just
    -0.93
     two
    -0.89
     London
    -0.85
     each
    -0.84
     in
    -0.84
     this
    -0.81
    それぞれ
    -0.81
    しました
    -0.80
     like
    -0.78
    POSITIVE LOGITS
     zerst
    1.04
     pesante
    1.01
     koniec
    1.01
    僰
    0.99
     koment
    0.99
     profonde
    0.99
     authors
    0.98
     campagne
    0.98
     carcasa
    0.97
     BEING
    0.97
    Activations Density 0.000%

    No Known Activations