© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 59421
    Prev
    Next
    INDEX
    Explanations

    death and circumstances

    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
     until
    -0.98
     now
    -0.98
     for
    -0.95
     которое
    -0.92
    ëren
    -0.89
    forChild
    -0.89
     once
    -0.88
     since
    -0.86
     sejak
    -0.86
    atici
    -0.86
    POSITIVE LOGITS
     of
    1.88
     at
    1.27
     leaving
    1.21
     due
    1.14
     sudden
    1.12
     aged
    1.10
     after
    1.05
     בבית
    1.03
     succ
    1.02
     from
    0.97
    Activations Density 0.046%

    No Known Activations