© 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-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 58720
    Prev
    Next
    INDEX
    Explanations

    connection or disconnection

    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
     реши
    0.45
     conoc
    0.43
    akn
    0.41
     buon
    0.40
    虍
    0.39
    峎
    0.39
    дук
    0.38
     જ
    0.38
     люд
    0.38
     lil
    0.37
    POSITIVE LOGITS
     reconnect
    0.46
    ConnectionType
    0.42
    ին
    0.41
    쐐
    0.38
     disconnection
    0.37
     disconnect
    0.37
    farwydd
    0.37
    ished
    0.37
     frustrated
    0.35
     disconnecting
    0.35
    Activations Density 0.002%

    No Known Activations