© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 54017
    Prev
    Next
    INDEX
    Explanations

    single, lonely, or unmarried individuals

    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
    最初
    0.43
     permissions
    0.36
     bureaucracy
    0.36
     gravity
    0.36
     Monkey
    0.36
     Nitro
    0.36
     glucocortic
    0.35
    霓
    0.35
    묵
    0.35
     nitro
    0.34
    POSITIVE LOGITS
     unmarried
    1.19
     одино
    1.11
     Single
    1.01
     singles
    1.01
     single
    1.00
    single
    0.96
    Single
    0.95
     lonely
    0.94
     Singles
    0.93
     loneliness
    0.92
    Activations Density 0.073%

    No Known Activations