© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59107
    Prev
    Next
    INDEX
    Explanations

    natural disasters and geological events

    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_10/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
     ondu
    -1.98
     abonnement
    -1.95
     vernis
    -1.88
    睃
    -1.87
     maniere
    -1.86
    
    -1.85
     feme
    -1.85
     specif
    -1.84
     alho
    -1.83
     industrie
    -1.82
    POSITIVE LOGITS
     all
    2.59
     with
    2.56
     to
    2.38
     on
    2.31
     that
    2.28
     very
    2.27
     at
    2.23
     during
    2.23
     in
    2.22
     without
    2.20
    Activations Density 0.050%

    No Known Activations