© 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. 48796
    Prev
    Next
    INDEX
    Explanations

    buoyancy or bu iş

    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
     I
    1.79
    n
    1.42
     It
    1.19
    ش
    1.18
    ↵
    1.12
    m
    1.10
    </h3>
    1.05
    iamo
    1.02
    กัน
    0.99
    I
    0.98
    POSITIVE LOGITS
     bu
    1.65
    ه
    1.57
    ية
    1.41
     Bucs
    1.36
     Bu
    1.34
    Bu
    1.34
    Бу
    1.34
     Buccaneers
    1.26
    {
    1.24
     هي
    1.22
    Activations Density 0.004%

    No Known Activations