© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 241337
    Prev
    Next
    INDEX
    Explanations

    Texas

    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
    IRT
    0.52
    NQ
    0.51
    Pes
    0.50
    奂
    0.50
    Logo
    0.50
     spok
    0.50
    IU
    0.49
    各国
    0.49
    ماغ
    0.49
    шк
    0.49
    POSITIVE LOGITS
    texas
    0.66
     dampers
    0.64
    텍
    0.63
     han
    0.61
     texas
    0.59
     sockets
    0.59
     texting
    0.59
     sausages
    0.58
     lockers
    0.57
     texts
    0.57
    Activations Density 0.000%

    No Known Activations