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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241333
    Prev
    Next
    INDEX
    Explanations

    LiDAR

    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_262k_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
    בו
    0.59
    automne
    0.52
     capacity
    0.50
    ることが
    0.49
     primavera
    0.49
    ባ
    0.48
    鮑
    0.48
    ץ
    0.48
    वाय
    0.48
    play
    0.47
    POSITIVE LOGITS
    უხ
    0.63
    Tort
    0.60
     Soldier
    0.59
    єкт
    0.59
     Эр
    0.57
     SER
    0.56
    .$
    0.56
     Regul
    0.56
     Tort
    0.55
     Соб
    0.55
    Activations Density 0.001%

    No Known Activations