© 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. 14836
    Prev
    Next
    INDEX
    Explanations

    ](

    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
     Prussia
    0.68
     Außen
    0.68
     Parry
    0.67
     jeux
    0.65
     
    0.65
     baron
    0.64
     ð
    0.63
    }(-\
    0.63
     puffed
    0.63
     Río
    0.61
    POSITIVE LOGITS
    javascript
    1.53
    mailto
    1.33
    JavaScript
    1.20
    Javascript
    1.13
     javascript
    1.05
    tel
    1.00
    showinfo
    0.95
     JavaScript
    0.92
    target
    0.89
     Javascript
    0.86
    Activations Density 0.002%

    No Known Activations