© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 30365
    Prev
    Next
    INDEX
    Explanations

    incoming connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     communicator
    0.45
     communic
    0.41
    শর
    0.39
     communicating
    0.38
     envoy
    0.38
     communicate
    0.38
     Duncan
    0.36
    망
    0.36
    见到
    0.36
     Comunicación
    0.35
    POSITIVE LOGITS
     incoming
    1.27
    Incoming
    1.25
     Incoming
    1.23
    incoming
    1.18
    Connections
    1.01
     connections
    0.97
    connections
    0.96
     Connections
    0.90
     conexiones
    0.88
    CONNE
    0.79
    Activations Density 0.002%

    No Known Activations