© 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. 87104
    Prev
    Next
    INDEX
    Explanations

    media outlets and news organizations

    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
     to
    -1.53
     and
    -1.39
     -
    -1.15
     –
    -1.05
    Announcement
    -0.95
     announcements
    -0.88
    どこに
    -0.88
    www
    -0.86
     announced
    -0.85
     się
    -0.84
    POSITIVE LOGITS
     about
    1.52
     why
    1.44
     after
    1.28
     \%}$
    1.22
    																				
    1.21
     earlier
    1.20
    reporter
    1.19
     prior
    1.19
     reporter
    1.13
     said
    1.10
    Activations Density 0.021%

    No Known Activations