© 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. 39102
    Prev
    Next
    INDEX
    Explanations

    sweet descriptor

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

    sweetness and "sweet spot"

    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
     souten
    0.65
    рист
    0.62
     кількість
    0.59
     Timurtaş
    0.58
     couche
    0.57
     созда
    0.56
    션
    0.56
    ет
    0.55
    いました
    0.55
    бой
    0.55
    POSITIVE LOGITS
    甜
    1.18
     sweet
    1.11
     sweeter
    1.00
    Sweet
    0.99
     Sweet
    0.95
     ngọt
    0.95
    sweet
    0.91
     sweetness
    0.89
    甜蜜
    0.84
    หวาน
    0.82
    Activations Density 0.023%

    No Known Activations