© 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. 22-GEMMASCOPE-RES-131K
    7. 15472
    Prev
    Next
    INDEX
    Explanations

    homicides suicides

    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_22/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
     now
    -1.15
    te
    -1.04
     They
    -1.03
    -1.03
    ↵↵
    -1.02
    par
    -1.02
     they
    -1.02
    in
    -0.96
    도록
    -0.95
    B
    -0.94
    POSITIVE LOGITS
     cases
    1.51
    Occasionally
    1.42
    extreme
    1.34
     kalend
    1.30
    individuals
    1.28
     rare
    1.26
     princesas
    1.24
    Sometimes
    1.23
    occurs
    1.23
     either
    1.22
    Activations Density 0.207%
    No Known Activations