© 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. 14086
    Prev
    Next
    INDEX
    Explanations

    lists and labels

    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
    hev
    0.61
     بالوں
    0.58
     آنے
    0.58
    手臂
    0.56
    灌
    0.55
     treinamento
    0.55
     capelli
    0.55
    UMI
    0.55
     menyebut
    0.54
    تاء
    0.54
    POSITIVE LOGITS
    ޏ
    0.61
     matéria
    0.55
     Bloch
    0.54
     lingers
    0.54
     Latham
    0.54
    START
    0.53
     Caen
    0.53
     lingered
    0.52
    বড়
    0.52
    ˩
    0.51
    Activations Density 0.000%

    No Known Activations