© 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. 40-GEMMASCOPE-2-RES-65K
    7. 2740
    Prev
    Next
    INDEX
    Explanations

    ages and years

    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_40_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
    isés
    0.29
    িয়াছে
    0.27
    [,,"
    0.27
     proporcional
    0.26
     cuantos
    0.26
     سبسڈی
    0.26
    㪇
    0.25
    ِلِّ
    0.25
     equilibria
    0.25
    сову
    0.25
    POSITIVE LOGITS
     years
    0.40
    th
    0.36
     सदस्यीय
    0.33
     metų
    0.33
     বছর
    0.32
    वीं
    0.31
    %
    0.31
     Jahre
    0.30
     Commandments
    0.30
    ️⃣
    0.29
    Activations Density 0.433%

    No Known Activations