© 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. 217439
    Prev
    Next
    INDEX
    Explanations

    "WORD" shall mean definition

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

    social constructs and concepts

    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
    ミ
    0.42
    ﾌ
    0.42
     sofistic
    0.41
     Fru
    0.40
     alleviate
    0.40
     contento
    0.39
    ઈ
    0.38
     famed
    0.38
     exquis
    0.38
     accentuate
    0.38
    POSITIVE LOGITS
    👬
    0.55
    âteaux
    0.50
    userService
    0.48
    mental
    0.47
    👮
    0.46
    keny
    0.45
    ើយ
    0.45
    ız
    0.45
     เพื่อน
    0.44
    👫
    0.44
    Activations Density 0.001%

    No Known Activations