© 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. 13320
    Prev
    Next
    INDEX
    Explanations

    company names

    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
     Jerusal
    0.59
     процент
    0.56
     그림
    0.55
     শহর
    0.53
     胸
    0.50
    ={}
    0.50
     نیم
    0.49
     крово
    0.49
    삵
    0.49
     まず
    0.49
    POSITIVE LOGITS
     Reliance
    1.00
    Reliance
    0.96
     Tata
    0.95
    Tata
    0.92
    reliance
    0.88
     Hindustan
    0.82
    Hind
    0.79
     reliance
    0.77
     Bajaj
    0.75
     Ess
    0.75
    Activations Density 0.076%

    No Known Activations