© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 34728
    Prev
    Next
    INDEX
    Explanations

    describes past states or actions

    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
     recente
    -1.03
    recently
    -1.00
    yesterday
    -0.99
     έχουν
    -0.99
    recent
    -0.99
     vorige
    -0.96
     έχει
    -0.96
     momente
    -0.96
    Been
    -0.96
    ɦ
    -0.95
    POSITIVE LOGITS
     was
    2.14
     shows
    1.98
     were
    1.61
     took
    1.61
     reveals
    1.59
     had
    1.56
     did
    1.56
     appears
    1.52
     went
    1.42
     became
    1.36
    Activations Density 0.144%

    No Known Activations