© 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. 15140
    Prev
    Next
    INDEX
    Explanations

    recently

    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
    <h4>
    1.17
       
    1.13
    Ace
    0.91
    ace
    0.85
     Ace
    0.85
    <blockquote>
    0.80
    ACE
    0.75
    Video
    0.75
    <h5>
    0.75
    <h3>
    0.73
    POSITIVE LOGITS
     related
    1.02
     RELATED
    0.98
     recientemente
    0.89
     recentemente
    0.89
     recently
    0.88
    related
    0.88
     relacionadas
    0.87
     недавно
    0.86
     récemment
    0.86
     relacionados
    0.85
    Activations Density 0.001%

    No Known Activations