© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 44149
    Prev
    Next
    INDEX
    Explanations

    sweetness or taste instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    मधील
    0.99
     diffé
    0.95
     Tecnología
    0.94
    ع
    0.93
    ◃
    0.90
     Ле
    0.88
     спів
    0.87
     artériel
    0.86
     Dishes
    0.86
    𝐼
    0.86
    POSITIVE LOGITS
    1.05
    out
    0.94
     lucrative
    0.89
    ning
    0.88
    ci
    0.88
    OUS
    0.87
    те
    0.86
    yd
    0.84
    ells
    0.83
    px
    0.83
    Activations Density 0.000%

    No Known Activations