© 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. 31-GEMMASCOPE-2-RES-65K
    7. 16298
    Prev
    Next
    INDEX
    Explanations

    SEE: prefixes

    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_31_width_65k_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
     a
    0.45
    $,
    0.39
     of
    0.38
    cdot
    0.38
    iation
    0.38
     件
    0.35
    $.
    0.34
    ]$,
    0.34
    IP
    0.34
     was
    0.33
    POSITIVE LOGITS
    ക്കാല
    0.48
     तस्वीरें
    0.47
     protrusions
    0.43
     परेश
    0.43
     नाखूनों
    0.43
     लाहिड़ी
    0.43
    ຕໍ່
    0.42
    தேசம்
    0.42
     ছবিতে
    0.42
    扪
    0.42
    Activations Density 0.003%

    No Known Activations