© 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. 60194
    Prev
    Next
    INDEX
    Explanations

    speaking, talking, writing

    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
    archical
    -0.96
     cremallera
    -0.93
     kuna
    -0.90
    celotti
    -0.89
     another
    -0.86
     zeigt
    -0.84
    ひたすら
    -0.84
     bernama
    -0.84
     SHOWS
    -0.83
     FORCES
    -0.83
    POSITIVE LOGITS
     speaking
    5.53
     Speaking
    4.34
    Speaking
    4.28
    speaking
    3.89
     speak
    3.22
     talking
    3.06
     spoke
    2.84
     in
    2.70
     speaks
    2.58
     writing
    2.38
    Activations Density 0.087%

    No Known Activations