© 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
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14148
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    M
    0.37
    J
    0.35
    N
    0.35
    K
    0.35
    C
    0.34
    S
    0.34
    R
    0.33
    D
    0.32
    B
    0.32
    O
    0.32
    POSITIVE LOGITS
     zyg
    0.33
     infinitesimal
    0.33
     pathophys
    0.33
     inguinal
    0.32
     parthen
    0.32
     abiotic
    0.32
     silage
    0.32
     condesc
    0.32
     arbitrage
    0.32
     asexual
    0.32
    Activations Density 0.013%

    No Known Activations