© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93246
    Prev
    Next
    INDEX
    Explanations

    AI adoption

    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_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
    0
    0.51
    (
    0.47
     marit
    0.46
    ved
    0.42
    فيق
    0.41
    리가
    0.41
     autopilot
    0.40
    пита
    0.40
    <0x80>
    0.40
    gação
    0.40
    POSITIVE LOGITS
     aversion
    0.46
     obscur
    0.46
     स्वातंत्र्य
    0.46
     obstruction
    0.45
     Deuter
    0.44
     пле
    0.44
     intercalation
    0.44
    宮城県
    0.43
     قرارداد
    0.43
     interdit
    0.43
    Activations Density 0.002%

    No Known Activations