© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3376
    Prev
    Next
    INDEX
    Explanations

    openings, curtains, doors, communication

    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/layer_16_width_262k_l0_medium
    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
    ু
    1.05
    在
    0.94
    ى
    0.94
    v
    0.93
     in
    0.93
     \
    0.93
    s
    0.90
    锟
    0.90
    ل
    0.90
    0.87
    POSITIVE LOGITS
    в
    0.88
     fermeture
    0.87
    is
    0.86
     aberta
    0.85
    ють
    0.84
    ?
    0.83
    ца
    0.82
     Open
    0.82
    ier
    0.81
     ouvert
    0.80
    Activations Density 0.151%

    No Known Activations