© 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. 177699
    Prev
    Next
    INDEX
    Explanations

    generational inheritance

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

    inheritance and legacy across generations

    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
    ين
    0.63
    大
    0.58
    ()
    0.57
    ated
    0.56
    BE
    0.56
    ă
    0.56
    <0x93>
    0.56
    age
    0.54
    中学
    0.53
    <0x9D>
    0.53
    POSITIVE LOGITS
     inheritance
    1.16
     Inheritance
    1.12
    传承
    1.11
     inherit
    1.08
     Inher
    1.03
    generational
    1.02
     legacies
    1.02
     hérit
    1.00
     насле
    0.99
     heirs
    0.98
    Activations Density 0.168%

    No Known Activations