© 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. 84181
    Prev
    Next
    INDEX
    Explanations

    catching up or talking

    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
     individuals
    -1.16
     individual
    -1.14
    Individual
    -1.05
     Individuals
    -1.05
     Individual
    -1.05
     INDIVIDUAL
    -0.99
     individ
    -0.96
     individuo
    -0.96
    Individuals
    -0.92
    individual
    -0.88
    POSITIVE LOGITS
     spoke
    2.56
     asked
    2.05
     chatted
    1.84
     caught
    1.73
     recently
    1.66
    spoke
    1.60
     sat
    1.59
     interviewed
    1.56
     chat
    1.55
     interview
    1.51
    Activations Density 0.048%

    No Known Activations