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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 12938
    Prev
    Next
    INDEX
    Explanations

    language, length, layers

    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
     l
    1.00
     lL
    0.85
     LD
    0.77
    LM
    0.76
     LM
    0.76
     LRC
    0.73
    LD
    0.73
    ltk
    0.72
     ls
    0.70
     ল
    0.69
    POSITIVE LOGITS
    anguage
    0.91
    anguages
    0.83
    ayout
    0.82
    ocation
    0.82
    ibraries
    0.80
    arger
    0.78
    ayers
    0.77
    ength
    0.77
    ayer
    0.77
    aterally
    0.76
    Activations Density 0.060%

    No Known Activations