© 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. 52189
    Prev
    Next
    INDEX
    Explanations

    father, inherited, dad

    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
     Friend
    0.47
     çoc
    0.45
     children
    0.44
     Friends
    0.44
    children
    0.43
     நட்ப
    0.43
     kinderen
    0.43
    乩
    0.43
    孩子
    0.42
     gyerek
    0.42
    POSITIVE LOGITS
     father
    1.48
    父
    1.43
     inherited
    1.41
     아버지
    1.38
     父
    1.34
     বাবার
    1.34
     отца
    1.34
     dad
    1.33
     পিতার
    1.31
     پدر
    1.31
    Activations Density 0.047%

    No Known Activations