© 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. 107705
    Prev
    Next
    INDEX
    Explanations

    all the

    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
    牍
    -0.93
    regalo
    -0.91
     πάντα
    -0.90
    pregunt
    -0.88
    everything
    -0.86
    Ucraina
    -0.86
    such
    -0.85
    Incluye
    -0.85
    Pendidikan
    -0.85
     vasca
    -0.82
    POSITIVE LOGITS
     these
    1.91
     those
    1.68
     this
    1.53
     этих
    1.23
     dieser
    1.21
     تلك
    1.09
    あの
    1.08
     diese
    1.08
    这些
    1.07
     này
    1.05
    Activations Density 0.012%

    No Known Activations