© 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-262K
    7. 28573
    Prev
    Next
    INDEX
    Explanations

    years of marriage

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

    years of marriage

    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_262k_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
    குழந்த
    0.41
    それぞれ
    0.41
    ന്ധി
    0.41
    ڡ
    0.41
    azir
    0.40
    க்க
    0.40
    傑
    0.40
     বয়স
    0.39
    Donc
    0.39
    樁
    0.39
    POSITIVE LOGITS
     sealed
    0.48
     reeling
    0.45
     inhaling
    0.45
     ironically
    0.44
     quilted
    0.44
     calling
    0.43
     crushes
    0.42
     call
    0.42
     explan
    0.42
     reel
    0.42
    Activations Density 0.007%

    No Known Activations