© 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. 13211
    Prev
    Next
    INDEX
    Explanations

    steps or movement

    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
    Hello
    0.55
     Hello
    0.54
    Declaration
    0.53
     problema
    0.52
    Business
    0.52
    Dear
    0.52
     문
    0.51
    故障
    0.51
     দেখেন
    0.51
     சொல்லி
    0.50
    POSITIVE LOGITS
    步
    0.68
     resembled
    0.65
     paso
    0.64
     sacrific
    0.64
     stepped
    0.64
     imit
    0.64
     Picchu
    0.64
     partisans
    0.63
     कदम
    0.60
     partisan
    0.59
    Activations Density 0.000%

    No Known Activations