© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15607
    Prev
    Next
    INDEX
    Explanations

    author or work

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    lica
    0.59
    걱
    0.56
    贤
    0.54
    聪
    0.54
     dispara
    0.53
    cuenta
    0.53
    指针
    0.52
    旗
    0.52
     episode
    0.52
     fué
    0.52
    POSITIVE LOGITS
     accompanies
    0.59
     Автор
    0.58
    Anthrop
    0.56
     introduces
    0.55
     Anthrop
    0.55
     তুম
    0.54
     attributed
    0.53
     произведение
    0.53
    NOTICE
    0.52
     knelt
    0.51
    Activations Density 0.000%

    No Known Activations