© 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-65K
    4. 15038
    Prev
    Next
    INDEX
    Explanations

    references

    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
    िंग्स
    0.55
     COMPLETE
    0.53
     चर्चित
    0.51
    ariales
    0.50
    ∅
    0.50
    toe
    0.50
    udi
    0.50
    ächer
    0.49
     tope
    0.48
    räume
    0.48
    POSITIVE LOGITS
     footnotes
    0.68
     sketches
    0.65
     essays
    0.63
     உறுப்பினர்
    0.63
     columns
    0.58
     clerks
    0.57
     Sketches
    0.56
    鐏
    0.56
     column
    0.55
     Essay
    0.55
    Activations Density 0.001%

    No Known Activations