© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7604
    Prev
    Next
    INDEX
    Explanations

    technical programming terms

    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_16k_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
     Zam
    0.34
     tanpa
    0.33
     todas
    0.33
     inseparable
    0.32
     R
    0.31
     Achilles
    0.30
     Leder
    0.29
     irrepar
    0.29
     uden
    0.29
    ynthesis
    0.28
    POSITIVE LOGITS
    jsdel
    0.35
    icional
    0.34
     ול
    0.33
     इंग
    0.33
     ба
    0.33
    𝒶
    0.33
     αρκε
    0.32
    𝚐
    0.32
     होश
    0.32
    伥
    0.32
    Activations Density 0.391%

    No Known Activations