© 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. 51428
    Prev
    Next
    INDEX
    Explanations

    measurement units and calculations

    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
     سہ
    0.39
    eze
    0.39
     preamble
    0.37
    顶点
    0.37
     平成
    0.37
     parchment
    0.37
    涉
    0.36
    第三
    0.36
    百姓
    0.36
    =-
    0.36
    POSITIVE LOGITS
    units
    0.48
     units
    0.48
     cm
    0.46
     yd
    0.45
    Units
    0.44
    单位
    0.42
     Cm
    0.42
    單位
    0.41
     CM
    0.40
    Cm
    0.39
    Activations Density 0.037%

    No Known Activations