© 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. 14042
    Prev
    Next
    INDEX
    Explanations

    technical specifications

    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
    FRINGEMENT
    0.58
     Thornton
    0.57
    Translate
    0.57
     sajana
    0.54
     فلسطینی
    0.54
    剽
    0.54
    ProductRunnable
    0.52
    ]['
    0.52
    Fres
    0.51
    اعدة
    0.51
    POSITIVE LOGITS
     வளாக
    0.61
    眼睛
    0.51
    仰
    0.50
     inches
    0.50
    odef
    0.50
    夲
    0.50
    rilor
    0.48
    mead
    0.48
    udit
    0.48
     Volume
    0.48
    Activations Density 0.000%

    No Known Activations