© 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. 16-GEMMASCOPE-2-RES-262K
    7. 47447
    Prev
    Next
    INDEX
    Explanations

    defining what something looks like

    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
    V
    1.11
    A
    1.05
    E
    0.97
    T
    0.88
    J
    0.87
    IN
    0.85
    O
    0.84
    AN
    0.84
    I
    0.83
    OB
    0.80
    POSITIVE LOGITS
    т
    0.74
    ت
    0.71
    ри
    0.67
    ا
    0.66
     Initiatives
    0.64
     ssid
    0.64
     Invalid
    0.63
     Contains
    0.62
     casts
    0.61
     prohibits
    0.61
    Activations Density 0.001%

    No Known Activations