© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12076
    Prev
    Next
    INDEX
    Explanations

    hobbies and free time activities

    np_acts-logits-general · gemini-2.5-flash-lite

    personal interests and hobbies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Career
    0.46
     coefficients
    0.45
     STD
    0.44
     হেন
    0.44
     Department
    0.42
     School
    0.42
     EIA
    0.42
    疚
    0.41
     Experience
    0.41
     coef
    0.41
    POSITIVE LOGITS
     hobbies
    0.81
    Hobbies
    0.73
     pesca
    0.67
     hobby
    0.66
     любит
    0.66
    hobby
    0.61
    趣味
    0.61
    が好き
    0.61
     snowboarding
    0.60
     graag
    0.59
    Activations Density 0.378%

    No Known Activations