© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65014
    Prev
    Next
    INDEX
    Explanations

    capture and collection activities

    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
    JpaRepository
    -1.00
    BUG
    -0.91
    ienia
    -0.91
     PLANT
    -0.88
    SEQUENCE
    -0.88
    렬
    -0.87
     pirated
    -0.86
     aphids
    -0.85
     производства
    -0.82
    ALIAN
    -0.82
    POSITIVE LOGITS
     trap
    3.11
     trapping
    2.80
     traps
    2.78
     Trap
    2.47
    trap
    2.45
     Traps
    2.30
    Trap
    2.20
     trapped
    2.20
     capture
    2.13
     bait
    1.73
    Activations Density 0.041%

    No Known Activations