© 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-IT
    5. 41-GEMMASCOPE-2-RES-65K
    7. 1344
    Prev
    Next
    INDEX
    Explanations

    open-weights model

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teore
    0.52
    passwd
    0.51
     paise
    0.51
     öd
    0.51
     mercedes
    0.50
     saldo
    0.49
     padassa
    0.49
    
    0.48
    鉀
    0.48
     teori
    0.48
    POSITIVE LOGITS
     Nation
    0.48
    став
    0.46
     Stark
    0.45
     Mission
    0.44
     Nations
    0.43
     النا
    0.43
     Nar
    0.42
     Nak
    0.42
    ారా
    0.42
    uzioni
    0.42
    Activations Density 0.094%

    No Known Activations