Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8744
    Prev
    Next
    INDEX
    Explanations

    research methods and problems

    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
     very
    -0.96
    brite
    -0.85
     ő
    -0.84
     sehr
    -0.84
     environnement
    -0.83
     似
    -0.83
    ということは
    -0.82
     comparaison
    -0.81
    oners
    -0.81
    reshold
    -0.79
    POSITIVE LOGITS
     Meanwhile
    0.91
     intrigu
    0.90
     fanci
    0.85
     Meine
    0.85
    扮演
    0.84
     ACTUALLY
    0.83
     retailing
    0.82
     meanwhile
    0.82
     feas
    0.81
    Meanwhile
    0.81
    Activations Density 0.065%

    No Known Activations