© 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. 98759
    Prev
    Next
    INDEX
    Explanations

    golden age or medal

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

    golden hour, age, touch

    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
    ২০
    0.55
    ू
    0.54
    اء
    0.53
    اہد
    0.52
    ών
    0.50
    اه
    0.49
    ᱘
    0.49
    اة
    0.48
    ıları
    0.48
     नहीं
    0.48
    POSITIVE LOGITS
     golden
    1.22
     золо
    1.22
    Golden
    1.16
     Golden
    1.16
     GOLD
    1.13
     gold
    1.12
     zlat
    1.09
     Gold
    1.09
     золото
    1.09
     금
    1.08
    Activations Density 0.497%

    No Known Activations