© 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-65K
    7. 14990
    Prev
    Next
    INDEX
    Explanations

    able

    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
     ईमानदारी
    0.59
    वेग
    0.52
    を行った
    0.51
    adau
    0.48
    舜
    0.48
     জানেন
    0.48
     કર્યા
    0.47
    堤
    0.47
     गौरव
    0.47
    চ্ছন্দ
    0.47
    POSITIVE LOGITS
     قابل
    3.22
    可
    3.17
     removable
    2.88
     editable
    2.80
     可
    2.75
    editable
    2.69
     controllable
    2.69
     replaceable
    2.69
     recoverable
    2.64
     readable
    2.63
    Activations Density 0.423%

    No Known Activations