© 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. 118507
    Prev
    Next
    INDEX
    Explanations

    explaining or discussing details

    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
    felizmente
    -1.05
     even
    -1.02
     aucune
    -1.00
     at
    -0.98
    assword
    -0.96
    してみて
    -0.95
     ask
    -0.93
     like
    -0.88
    Lihat
    -0.86
     any
    -0.85
    POSITIVE LOGITS
     discussing
    1.27
     guide
    1.23
     discusses
    1.17
     discussed
    1.15
     briefly
    1.13
     details
    1.11
     discuss
    1.10
     discussion
    1.06
     detailed
    1.06
     detail
    1.02
    Activations Density 0.056%

    No Known Activations