© 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. 103898
    Prev
    Next
    INDEX
    Explanations

    celebrity recent 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
     their
    -0.96
    alimentos
    -0.95
    >);
    -0.95
    🤚
    -0.95
     with
    -0.94
    новременно
    -0.93
    datable
    -0.92
    ="_
    -0.88
    дизайн
    -0.88
    になるので
    -0.87
    POSITIVE LOGITS
     recently
    1.68
     previously
    1.36
     shared
    1.31
     isn
    1.22
     hasn
    1.16
     recentemente
    1.09
     posted
    1.08
    以前
    1.05
    最近
    1.03
     hil
    1.01
    Activations Density 0.032%

    No Known Activations