© 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. 48936
    Prev
    Next
    INDEX
    Explanations

    father figure

    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
     caregiver
    0.42
     наші
    0.42
    Our
    0.42
    Sharma
    0.41
    쌤
    0.41
    Method
    0.41
    Logical
    0.40
     наших
    0.39
    赋予
    0.39
     daycare
    0.38
    POSITIVE LOGITS
     father
    1.16
     père
    0.98
    father
    0.98
     отец
    0.95
     patriarch
    0.95
     grandfather
    0.94
     पिता
    0.90
    父
    0.89
    父親
    0.87
     پدر
    0.86
    Activations Density 0.025%

    No Known Activations